* Updating the workflow to publish to the new marketplace branch
Using env vars for the branch names so that we can easily update without inlining everything as we progress through
* Potential fix for pull request finding
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Foundation skill (flowstudio-power-automate-mcp) rewritten to use the
server's new tool_search and list_skills meta-tools (v1.1.5+) for
discovery instead of cataloging every tool by hand. Cut from 519 to
295 lines. New "Which Skill to Use When" intent-keyed decision tree
points at the four specialized skills.
Build/debug/governance/monitoring updated for use-case framing. Tools
that genuinely cross tiers (e.g. debug skill borrowing
get_store_flow_summary) are correct when the workflow needs them — the
split between skills is by use-case intent, not by tool partition.
Build skill: new Step 3a Resolving Dynamic Connector Values covers
get_live_dynamic_options outer-parameter auto-bridge (v1.1.6+) and the
AadGraph user-picker fallback via shared_office365users.SearchUserV2
(replaces broken builtInOperation:AadGraph.GetUsers).
Debug skill: Outlook user-picker failure note pointing at the fallback.
Monitoring skill description disambiguates from the server's monitor-flow
tool bundle (runtime control of a single flow) — this skill is
tenant-wide health analytics over the cached store.
All 5 skills validate via npm run skill:validate; line endings LF only;
codespell clean; auto-regenerated docs/README.skills.md included.
- Add shell completion section: copilot completion <bash|zsh|fish>
subcommand for static shell tab-completion scripts (v1.0.37)
- Add warning that ~/.claude/ agents/skills/commands are no longer
loaded by Copilot CLI; point to ~/.agents/ as the correct location (v1.0.36)
- Document ctrl+x → b keyboard shortcut for backgrounding running
tasks (v1.0.39)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Introduce a new github-release skill: adds skills/github-release/SKILL.md with a 9-step GitHub release workflow (gh/git-based, SemVer, Keep a Changelog guidance). Also adds reference heuristics for commit classification and SemVer decision rules, and updates docs/README.skills.md to list the new skill.
* Add ai-ready skill (wrapper)
Lightweight wrapper that installs the full ai-ready skill from
johnpapa/ai-ready and runs it. The full skill (~600 lines) analyzes
repos and generates AGENTS.md, copilot-instructions.md, CI workflows,
issue templates, and more — all customized to the repo's actual stack.
Wrapper approach keeps this repo's review surface small (30 lines)
while the source of truth stays in johnpapa/ai-ready.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix: use numbered steps to satisfy skill validator
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix: address Copilot review feedback
- Quote frontmatter description (YAML consistency)
- Add PowerShell install commands for cross-platform support
- Clarify that download overwrites existing copy
- Add note about pinning to a specific tag/commit
- Explicit invocation instructions (say 'make this repo ai-ready')
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* docs: add ai-ready to skills index table
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix: correct ai-ready skill alphabetical order in README.skills.md
Run npm run build to fix the entry ordering that caused CI failure.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix: add review step before loading downloaded skill
Address code review feedback — users should inspect the downloaded
SKILL.md before reloading skills, per supply chain safety suggestion.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* feat: add hooks authoring instruction
Add hooks.instructions.md with portable guidance for writing GitHub Copilot hooks:
- Folder structure, config schema, and all field documentation
- Script contract: stdin JSON, exit codes, stdout/stderr channels
- Payload schemas for all common events (sessionStart, sessionEnd, userPromptSubmitted, preToolUse, postToolUse, errorOccurred, agentStop)
- Per-event deny mechanisms (structured JSON for preToolUse, non-zero exit for others)
- Matcher support for host-level tool filtering
- Three impactful examples: commit gate, auto-format, dangerous command blocker
- Bash and PowerShell templates
- Cross-platform guidance (Python through both entries)
- Anti-patterns, design rules, and portability notes (GitHub Copilot vs Claude Code)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix: address PR review comments
- Document both toolArgs (JSON string) and tool_input/toolInput (object) variants with defensive parsing
- Update sessionStart stdout to reflect additionalContext injection support
- Document preToolUse stdout output fields: modifiedArgs/updatedInput, additionalContext
- Add matcher field note about local verification
- Remove undocumented notification event from event table
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix: address round 2 review comments
- Defensive toolArgs parsing in all 3 example scripts (handle toolArgs string, tool_input, toolInput)
- PowerShell type check: test -is [string] before ConvertFrom-Json, init to null
- commit-gate.sh: add package.json existence guard before jq
- block-dangerous.sh: truncate command in deny reason and stderr to avoid leaking secrets
- Consistent defensive parsing helper across all Bash examples
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix: handle toolArgs as string or object in jq, fix short_cmd scoping
- All 3 Bash example jq blocks now check toolArgs type before fromjson
- short_cmd defined before the deny/log branch to avoid set -u error
- Consistent defensive pattern across commit-gate, format-on-save, block-dangerous
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix: remove accidentally committed agency.toml
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix: expand Portability Note into CLI vs VS Code vs Cloud Agent section
Address Aaron's review: replace the thin portability bullet points with
a concrete comparison table covering what is the same (config schema,
event name casing, fields) and what differs (hook loading, shell
environment, tool argument field names). Add a 'How to write portable
hooks' checklist. Separate Claude Code into its own subsection.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix: simplify to toolArgs-only parsing, clean portability section
- toolArgs is the documented contract — remove tool_input/toolInput defensive
fallbacks from all examples and the Script Contract template
- Simplify portability section: same config everywhere, one-line note about
cloud agent requiring default branch
- All 3 example scripts now use simple toolArgs pipe parsing
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add pr-dashboard skill and plugin
Adds a self-contained PR dashboard skill that generates and opens a
rich HTML dashboard in the browser showing GitHub pull requests for a
given date range and role filter.
- Skill: skills/pr-dashboard/ — bundles pr-dashboard-cli.mjs,
dashboard.html, and lib/utils.mjs
- Plugin: plugins/pr-dashboard/ — makes it installable via
`copilot skill install pr-dashboard@awesome-copilot`
Requires GitHub CLI (gh) installed and authenticated.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Restore README.instructions.md to upstream sort order
macOS locale sorts Japanese/Korean C# entries differently than Linux CI.
Restore to the upstream/staged version since we don't add any instructions.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Address PR review comments
- Fix regex character class bug: [-to]+ → (?:-|to) alternation in utils.mjs
- Fix 'last week' to return previous calendar week (Mon–Sun) not last 7 days
- Remove unused formatHumanDate and buildMarkdown exports from utils.mjs
- Fix ghApi error handling: rethrow with helpful message instead of silently
returning parsed JSON on failure (prevents silent auth errors)
- Add pagination to searchIssues (up to 1000 results across pages)
- Add rel="noopener noreferrer" to target=_blank links in generated rows
- HTML-escape fallback template content in renderHtml to prevent injection
- Move escapeHtml to module level so it's available before renderHtml body
- Neutralise dashboard.html template: placeholder title/h1/meta/stats/tbody
- Empty __md and filename in template (CLI populates at runtime)
- Add aria-label to search input and status/review selects
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* remove newline
* Regenerate docs/README.instructions.md
* refactor(pr-dashboard): move scripts/assets per skills spec, remove plugin
- Move pr-dashboard-cli.mjs and lib/utils.mjs into scripts/ per skills spec
- Move dashboard.html into assets/ per skills spec
- Update CLI template path and SKILL.md script path reference
- Remove plugins/pr-dashboard (redundant now that gh skills install works)
- Clean up marketplace.json and docs/README.plugins.md
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Removing search from the home pageThis was a little confusing because there are two searches, but the overall site search is a lot more powerful
* Prefilter website search by resource page
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* small error handling and formatting
* Simplify website listing controls
Remove per-page text search, trim page-specific controls, and move remaining sort/filter controls into compact flyouts.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Three agent files had a trailing comma after the last element in their
YAML flow-sequence tools arrays. When parsed, this produces an empty
string as an extra tool entry, which the Copilot API rejects with:
CAPIError: 400 Invalid 'tools[N].function.name': empty string
Affected files:
- agents/kusto-assistant.agent.md
- agents/mentoring-juniors.agent.md
- agents/address-comments.agent.md
Co-authored-by: ilderaj <>
* feat: move to xml top tags for ebtter llm parsing and structure
- Orchestrator is now purely an orchestrator
- Added new calrify phase for immediate user erequest understanding and task parsing before workflow
- Enforce review/ critic to plan instea dof 3x plan generation retries for better error handling and self-correction
- Add hins to all agents
- Optimize defitons for simplicity/ conciseness while maintaining clarity
* feat(critic): add holistic review and final review enhancements
* chore: bump marketplace version to 1.10.0
- Updated `.github/plugin/marketplace.json` to version 1.10.0.
- Revised `agents/gem-browser-tester.agent.md` to improve the BROWSER TESTER role documentation with a clearer structure, explicit role header, and organized knowledge sources section.
* refactor: streamline verification and self‑critique steps across browser‑tester, code‑simplifier, critic, and debugger agents
* feat(researcher): improve mode selection workflow and research implementation details
- Refine **Clarify** mode description to emphasize minimal research for detecting ambiguities.
- Reorder steps and clarify intent detection (`continue_plan`, `modify_plan`, `new_task`).
- Add explicit sub‑steps for presenting architectural and task‑specific clarifications.
- Update **Research** mode section with clearer initialization workflow.
- Simplify and reformat the confidence calculation comments for readability.
- Minor formatting tweaks and added blank lines for visual separation.
* Update gem-orchestrator.agent.md
* docs(gem-browser-tester): enhance BROWSER TESTER role description and clarify workflow steps- Expanded the BROWSER TESTER role with explicit responsibilities and constraints
- Reformatted the Knowledge Sources list using consistent numbered items for readability- Updated the Workflow section to detail initialization, execution, and teardown steps more clearly- Refined the Output Format and Research Format Guide structures to use proper markdown syntax
- Improved overall formatting and consistency of documentation for better maintainability
* docs: fix typo in delegation description
* Add ai-team-orchestration plugin: multi-agent dev team with Producer, Dev Team, QA agents
* fix: use kebab-case agent names to match filenames
* fix: regenerate README after agent name change
* fix: address Copilot review — add edit tools to Producer/QA, use GitHub closing keywords
* fix: update agent tools to official VS Code tool set names
Replace outdated/nonexistent tool names with current official tool sets:
- Producer: search, read, edit, web (removed nonexistent githubRepo)
- Dev Team: search, read, edit, execute, web (replaced runCommands, problems, usages, etc.)
- QA: search, read, edit, execute, web (removed nonexistent findTestFiles, runTests)
Ref: https://code.visualstudio.com/docs/copilot/reference/copilot-vscode-features#_chat-tools
* fix: remove frontmatter from plugin README per reviewer feedback
---------
Co-authored-by: Aaron Powell <me@aaron-powell.com>
* removing old scripts
* consolidated folder
* Updating usage of scripts
* Adding script to generate an open PR report, rather than making AI gen it each time
* Adding step to close old quality report discussions
- Document new HTTP hook type (v1.0.35): hooks can now POST JSON to a URL
instead of running a local command, enabling centralized audit/notification
services without distributing scripts to every developer's machine
- Document preToolUse matcher field (v1.0.36): clarify that matcher is a regex
filter on tool name; add important upgrade note about v1.0.36 behavioral fix
(previously matcher was silently ignored)
- Update Security Gating example to show matcher field targeting the bash tool
- Add HTTP hook practical example for session-end audit webhook
- Note that plugins take effect immediately after install (v1.0.35, no restart needed)
- Update lastUpdated dates on both pages
Sources:
- https://github.com/github/copilot-cli/releases/tag/v1.0.35
- https://github.com/github/copilot-cli/releases/tag/v1.0.36
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add migration guide from javax to jakarta namespace
This document provides a comprehensive guide for migrating Java code from the javax namespace to the jakarta namespace, including steps for scanning, updating dependencies, and verifying the migration.
* Add javax to jakarta migration skill entry
* fix: correct link for adding agents in CONTRIBUTING.md
removing outdated prompts-link
* feat: add Terminal Helper agent for PowerShell and Bash command assistance
* fix: rename task to validate-plugins and update command details
as collections are outdated
https://github.com/github/awesome-copilot/pull/717
* update name format for terminal helper to lowercase
* update scope description for terminal context clarity
* Add vardoger-analyze skill
Made-with: Cursor
* fix Copilot session-state path in vardoger-analyze SKILL.md
* add numbered workflow overview to satisfy skill-validator
The dotnet/skills validator's NumberedStepRegex (^\d+\.\s, multiline)
only matches ordered list items at line start, not ### numbered
headings, so the previous '### 1. …' layout triggered the
'No numbered workflow steps' warning on PR #1461. Keep the existing
step headings for structure and add a short numbered Workflow
summary that the regex picks up.
* regenerate docs/README.skills.md for vardoger-analyze
* Add resemble-detect skill
Deepfake detection and media safety skill using Resemble AI — detects
AI-generated audio, images, video, and text with confidence scores,
traces audio source platforms, applies and reads watermarks, verifies
speaker identity, and extracts media intelligence (speaker, emotion,
misinformation signals).
Packaged as SKILL.md + LICENSE (Apache-2.0). Generated docs updated
via npm start per CONTRIBUTING.md.
* resemble-detect: trim body under 500 lines + add compatibility
Moves detailed request/response schemas from SKILL.md into
references/api-reference.md, bringing the SKILL body from 557 to
282 lines (validator hard cap is 500). Core decision-making content
— capability decision tree, score interpretation, workflows, red
flags — stays in the body where the agent needs it at query time.
Also adds a compatibility field to frontmatter per review feedback:
surfaces the RESEMBLE_API_KEY requirement and the public-HTTPS-URL
constraint upfront.
* Fix resemble-detect skill metadata
