[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JGSN9RF2EBGNEEBTN8JA4N":3,"skill-same:01M6JGSN9RF2EBGNEEBTN8JA4N":73},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":13,"repositoryHtmlUrl":56,"repositoryHomepageUrl":6,"ownerHtmlUrl":57,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":58,"install":59,"resources":72},"01M6JGSN9RF2EBGNEEBTN8JA4N","brag-sheet",null,"Turn vague \"what did I do?\" into evidence-backed impact statements for performance reviews, self-reviews, promotion packets, and weekly updates. Uniquely mines Copilot CLI session logs to reconstruct forgotten work, plus git commits and GitHub PRs. Enforces a 3-part impact contract (action → result → evidence). Works standalone with zero dependencies. Trigger for: \"brag\", \"log work\", \"what did I do\", \"backfill my work history\", \"performance review\", \"self-review\", \"self assessment\", \"write impact statement\", \"review prep\", \"promo packet\", \"promotion case\", \"weekly update\", \"status report\", \"accomplishments\", \"what did I ship\", \"I forgot to log my work\", \"summarize my work\", \"track my wins\", \"what should I highlight\", \"end of half\", \"career growth\", \"work journal\", or any request to document, summarize, or organize work accomplishments.","JiayiV\u002Fquestion_mixing","JiayiV","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54466889?v=4","01M6JFJYYMRZ3QRGP9339JNQ2K","01M6JFJZ35KB0QVT50NAHPJA7G",0,"MIT","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fbrag-sheet\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"brag sheet","brag","sheet","log","vague","weekly","reviews","github copilot cli","impact","status report","time","macos","write","gh cli","ship","logs","git","update","assessment","status","2026-11-10 10:12:30",false,"---\nname: brag-sheet\ndescription: >\n  Turn vague \"what did I do?\" into evidence-backed impact statements for performance\n  reviews, self-reviews, promotion packets, and weekly updates. Uniquely mines Copilot\n  CLI session logs to reconstruct forgotten work, plus git commits and GitHub PRs.\n  Enforces a 3-part impact contract (action → result → evidence). Works standalone\n  with zero dependencies. Trigger for: \"brag\", \"log work\", \"what did I do\",\n  \"backfill my work history\", \"performance review\", \"self-review\", \"self assessment\",\n  \"write impact statement\", \"review prep\", \"promo packet\", \"promotion case\",\n  \"weekly update\", \"status report\", \"accomplishments\", \"what did I ship\",\n  \"I forgot to log my work\", \"summarize my work\", \"track my wins\",\n  \"what should I highlight\", \"end of half\", \"career growth\", \"work journal\",\n  or any request to document, summarize, or organize work accomplishments.\nlicense: MIT\ncompatibility: 'Cross-platform (Windows, macOS, Linux). Works with any GitHub Copilot CLI session. Optional: git, gh CLI.'\nmetadata:\n  version: \"1.1\"\nargument-hint: 'Optional: time range (\"last 2 weeks\", \"this half\"), category (\"infrastructure\"), \"backfill\", or \"review prep\"'\n---\n\n# Brag Sheet — Work Impact Writer\n\nTurn engineering work into evidence-backed impact statements for performance reviews, self-reviews, promotion packets, and weekly updates. Uniquely mines Copilot CLI session logs, git history, and PRs to reconstruct forgotten work.\n\nUSE FOR: \"brag\", \"log work\", \"what did I do\", \"backfill\", \"performance review\", \"self-review\", \"promo packet\", \"weekly update\", \"status report\", \"write impact statement\", \"what did I ship\", \"I forgot to log my work\", \"review prep\", \"accomplishments\"\nDO NOT USE FOR: project management, sprint planning, time tracking, ticket creation\n\n## Quick Start\n\n| User wants... | Mode | Output |\n|---------------|------|--------|\n| Log one accomplishment | **Capture** | 1 impact-first entry |\n| \"What did I do last week?\" | **Backfill** | Entries grouped by week, mined from git\u002FPRs\u002Fsessions |\n| Prep for review or promo | **Review Pack** | Entries grouped by impact theme + STAR narratives |\n\n## Agent Behavior Rules\n\n1. **DO** confirm the time range and scope before scanning sources. Don't assume \"last week\" — ask.\n2. **DO** check which tools are available (`save_to_brag_sheet`, `git`, `gh`) before choosing a workflow.\n3. **DO** always include all three parts: action → result → evidence. If evidence is missing, write `(evidence needed)` — never silently omit.\n4. **DO** show drafted entries to the user before saving. Never auto-save without confirmation.\n5. **DO** group related commits into a single entry. Ten commits on the same feature = one entry.\n6. **DO** preserve the user's voice. Reframe for impact, but don't invent accomplishments or inflate scope.\n7. **DO NOT** fabricate metrics, team sizes, or impact numbers. If the user doesn't provide a number, don't invent one.\n8. **DO NOT** write entries for work the user only described verbally without verifying. Ask: \"Did this ship? Is there a PR or doc I can reference?\"\n9. **DO NOT** skip the backfill scan steps or draft entries before scanning is complete.\n10. **DO NOT** pad weak periods with trivial entries. An honest gap is better than inflated fluff.\n\n## Entry Format\n\nEvery entry uses impact-first framing with three required parts:\n\n```\nDid [action] → [result\u002Fimpact] → [evidence]\n```\n\n**Do not output an entry unless it includes all three parts.** If evidence is missing, ask for it or mark as \"(evidence needed)\".\n\n### Anti-Patterns\n\n| ❌ Don't | ✅ Do instead |\n|---------|--------------|\n| \"Fixed a bug in auth\" | \"Fixed token refresh race condition → eliminated 401s affecting 12% of API calls → PR #247\" |\n| \"Worked on dashboards\" | \"Built latency dashboard in Grafana → on-call detects P95 spikes in \u003C2min → deployed to prod\" |\n| Invent a metric: \"saved 40% of eng time\" | Ask: \"Do you have a rough estimate, or should I keep this qualitative?\" |\n| One entry per commit | Group related commits into one entry with highest-impact framing |\n| Passive voice: \"The pipeline was improved\" | Active voice: \"Built CI matrix → caught Windows-only bug before release\" |\n| List technologies used | State the outcome: \"Migrated 4 services to IaC → deploy time 45min → 8min\" |\n| Silently drop weak entries | Mark `(evidence needed)` and present for user to fill in |\n\n## Evidence Ladder\n\nNot every entry needs a metric. Use the strongest evidence available:\n\n| Strength | Evidence type | Example |\n|----------|--------------|---------|\n| ? Best | Quantified metric | \"Reduced P95 latency from 800ms to 120ms\" |\n| ? Strong | PR, commit, or doc link | \"PR #312, design doc in wiki\" |\n| ? Good | Observable outcome | \"Unblocked Team X\", \"Resolved Sev2 incident Y\" |\n| ✅ Acceptable | Qualitative + context | \"Reduced toil for on-call rotation — see updated runbook\" |\n| ⚠️ Weak | Activity only | \"Worked on auth\" — reframe or mark `(evidence needed)` |\n\nNever invent a metric to fill the gap. Qualitative evidence with context beats fabricated numbers.\n\n## Categories\n\n| ID | Emoji | Use for |\n|----|-------|---------|\n| `pr` | ? | Merged PRs, shipped features |\n| `bugfix` | ? | Bug fixes, incident patches |\n| `infrastructure` | ?️ | Infra, deployments, migrations |\n| `investigation` | ? | Root cause analysis, debugging |\n| `collaboration` | ? | Reviews, mentoring, design discussions |\n| `tooling` | ? | Dev tools, scripts, automation |\n| `oncall` | ? | Incident response, on-call wins |\n| `design` | ? | Design docs, architecture decisions |\n| `documentation` | ? | Docs, runbooks, guides |\n\n## How to Help the User\n\nFollow this decision tree:\n\n1. **If `save_to_brag_sheet` tool is available** → use extension tools directly (`save_to_brag_sheet`, `review_brag_sheet`, `generate_work_log`). Do not reference or attempt to call these tools unless they are confirmed available.\n\n2. **If git or gh CLI is available** → backfill from commits and PRs (see Backfill section below)\n\n3. **Otherwise** → guided interview: \"What did you work on?\", \"Who benefited?\", \"What's the evidence?\"\n\nFor each entry, walk through: **What** (the deliverable) → **Why** (who benefits) → **Evidence** (PR, metric, link). Output formatted markdown the user can paste into a review doc.\n\n## Backfill Workflow\n\nWhen the user asks \"what did I do last week\" or \"backfill my history\":\n\n**Follow these steps in order. Do not draft entries until scanning is complete.**\n\n### Step 1: Scan available sources\n\nCheck what's available, then mine each source:\n```bash\ngit --version 2>\u002Fdev\u002Fnull         # for commit mining\ngh --version 2>\u002Fdev\u002Fnull          # for PR mining\nls ~\u002F.copilot\u002Fsession-state\u002F 2>\u002Fdev\u002Fnull  # Copilot session logs\n```\n\n**Git commits** — recent commits by the user in the current repo:\n```bash\ngit log --author=\"$(git config user.email)\" --since=\"2 weeks ago\" \\\n  --pretty=format:'%h|%ad|%s' --date=short --no-merges\n```\n\n**PR history** — merged PRs across repos:\n```bash\ngh pr list --author @me --state merged --limit 20 \\\n  --json number,title,repository,mergedAt\n```\n\n**Copilot session history** (unique to this skill):\n- Path: `~\u002F.copilot\u002Fsession-state\u002F\u003Csession-id>\u002Fworkspace.yaml`\n- Read fields: `summary`, `cwd`, `repository`, `branch`\n- Skip sessions without a `summary` field\n- Note: this directory may not exist on all machines\n\nIf none of these sources are available, fall back to the guided interview.\n\n### Step 2: Group related work\n\nCluster related signals into one entry:\n- Same PR + its commits → 1 entry\n- Multiple commits on the same file\u002Ffeature within 3 days → 1 entry\n- Copilot sessions referencing the same repo + branch → merge into PR entry if one exists\n\n### Step 3: Draft entries\n\nWrite impact-first entries for each group. Assign categories.\n\n### Step 4: Present and refine\n\nShow all drafted entries to the user. Adjust based on feedback.\n\n### Step 5: Output\n\nFormat as markdown grouped by week:\n\n```markdown\n## Week of 2025-04-14\n\n### ? PRs & Features\n- **Migrated auth service to managed identity** → eliminated 3 secret rotation incidents\u002Fquarter → PR #312\n\n### ?️ Infrastructure\n- **Built CI pipeline for copilot-brag-sheet** → 107 tests across 3 OSes × 3 Node versions → shipped v1.0.0\n```\n\n## Performance Review Prep\n\nWhen the user is preparing for a performance review (Connect, annual review, etc.):\n\n### Structure\n\n1. **Gather** — collect entries from the work log (or backfill using the workflow above)\n2. **Select** — pick the top 3–5 highest-impact items\n3. **Rewrite** each item with three parts:\n   - **What I did** — the specific action\n   - **Why it mattered** — who benefited, what changed\n   - **Proof** — PR number, metric delta, dashboard link, customer outcome\n4. **Organize** by impact theme (not chronologically):\n   - Delivering results \u002F operational excellence\n   - Customer \u002F team impact\n   - Collaboration \u002F mentoring \u002F leadership\n   - Growth \u002F learning\n5. **Ask for gaps** — if evidence is missing, prompt the user: \"What metric changed?\", \"Who was unblocked?\", \"What's the PR or incident ID?\"\n\n### Strong vs weak entries\n\n| ✅ Strong | ❌ Weak |\n|----------|--------|\n| Outcome-first, quantified | Activity list (\"worked on X\") |\n| Tied to customer\u002Fteam impact | No beneficiary mentioned |\n| Includes evidence (PR, metric) | No measurable result |\n| Shows ownership or leadership | Pure task completion |\n\n### Narrative format\n\nFor longer narrative sections, use STAR: **S**ituation → **T**ask → **A**ction → **R**esult.\n\nFor Microsoft employees using the Connect preset, frame entries around Core Priorities: delivering results, customer obsession, teamwork, and growth mindset.\n\n## Output Contract\n\nBefore finishing, ensure:\n1. Every entry has action → result → evidence (mark `(evidence needed)` if missing)\n2. No fabricated metrics — only user-provided or source-verified data\n3. Entries shown to user before saving\n4. Time range explicitly stated\n5. Output is pasteable markdown with categories assigned\n\n## Gotchas\n\n### No recent commits in the current repo\nThe user may work across multiple repos. Before concluding there's nothing to backfill:\n1. Ask if they want to scan a different repo or branch\n2. Check `gh pr list --author @me --state merged` for cross-repo PRs\n3. Fall back to the guided interview — not all impactful work leaves git traces (design docs, incident response, mentoring)\n\n### Review period doesn't match git history\nPerformance reviews often cover 6–12 months. Explicitly set the date range:\n```bash\ngit log --author=\"$(git config user.name)\" --since=\"2024-07-01\" --until=\"2025-01-01\" --oneline\n```\nPR history (`gh pr list --state merged`) is more reliable for long time ranges than commit logs.\n\n### User can't quantify impact\nNot every entry needs a number. See the Evidence Ladder above. Acceptable evidence includes PR links, \"unblocked Team X\", or qualitative outcomes with context. Never invent a metric to fill the gap.\n\n### Copilot session directory doesn't exist\n`~\u002F.copilot\u002Fsession-state\u002F` only exists if the user has run Copilot CLI sessions. Don't error — silently skip and note: \"No Copilot session history found; scanning git and PRs only.\"\n\n### \"brag\" might mean something else\nThe user might say \"brag about this feature to my team\" (a launch announcement, not a work entry). Confirm intent if ambiguous.\n\n### Pair programming or co-authored commits\nIf multiple authors appear on the same commits, ask: \"Should I credit this as your work, shared work, or skip it?\"\n\n## Automatic Session Tracking (Optional)\n\nFor automatic background tracking of every Copilot CLI session (files edited, PRs created, git actions), install the [copilot-brag-sheet](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcopilot-brag-sheet) extension. It adds `save_to_brag_sheet`, `review_brag_sheet`, and `generate_work_log` tools to every session.\n","# Brag Sheet — Work Impact Writer\n\nTurn engineering work into evidence-backed impact statements for performance reviews, self-reviews, promotion packets, and weekly updates. Uniquely mines Copilot CLI session logs, git history, and PRs to reconstruct forgotten work.\n\nUSE FOR: \"brag\", \"log work\", \"what did I do\", \"backfill\", \"performance review\", \"self-review\", \"promo packet\", \"weekly update\", \"status report\", \"write impact statement\", \"what did I ship\", \"I forgot to log my work\", \"review prep\", \"accomplishments\"\nDO NOT USE FOR: project management, sprint planning, time tracking, ticket creation\n\n## Quick Start\n\n| User wants... | Mode | Output |\n|---------------|------|--------|\n| Log one accomplishment | **Capture** | 1 impact-first entry |\n| \"What did I do last week?\" | **Backfill** | Entries grouped by week, mined from git\u002FPRs\u002Fsessions |\n| Prep for review or promo | **Review Pack** | Entries grouped by impact theme + STAR narratives |\n\n## Agent Behavior Rules\n\n1. **DO** confirm the time range and scope before scanning sources. Don't assume \"last week\" — ask.\n2. **DO** check which tools are available (`save_to_brag_sheet`, `git`, `gh`) before choosing a workflow.\n3. **DO** always include all three parts: action → result → evidence. If evidence is missing, write `(evidence needed)` — never silently omit.\n4. **DO** show drafted entries to the user before saving. Never auto-save without confirmation.\n5. **DO** group related commits into a single entry. Ten commits on the same feature = one entry.\n6. **DO** preserve the user's voice. Reframe for impact, but don't invent accomplishments or inflate scope.\n7. **DO NOT** fabricate metrics, team sizes, or impact numbers. If the user doesn't provide a number, don't invent one.\n8. **DO NOT** write entries for work the user only described verbally without verifying. Ask: \"Did this ship? Is there a PR or doc I can reference?\"\n9. **DO NOT** skip the backfill scan steps or draft entries before scanning is complete.\n10. **DO NOT** pad weak periods with trivial entries. An honest gap is better than inflated fluff.\n\n## Entry Format\n\nEvery entry uses impact-first framing with three required parts:\n\n```\nDid [action] → [result\u002Fimpact] → [evidence]\n```\n\n**Do not output an entry unless it includes all three parts.** If evidence is missing, ask for it or mark as \"(evidence needed)\".\n\n### Anti-Patterns\n\n| ❌ Don't | ✅ Do instead |\n|---------|--------------|\n| \"Fixed a bug in auth\" | \"Fixed token refresh race condition → eliminated 401s affecting 12% of API calls → PR #247\" |\n| \"Worked on dashboards\" | \"Built latency dashboard in Grafana → on-call detects P95 spikes in \u003C2min → deployed to prod\" |\n| Invent a metric: \"saved 40% of eng time\" | Ask: \"Do you have a rough estimate, or should I keep this qualitative?\" |\n| One entry per commit | Group related commits into one entry with highest-impact framing |\n| Passive voice: \"The pipeline was improved\" | Active voice: \"Built CI matrix → caught Windows-only bug before release\" |\n| List technologies used | State the outcome: \"Migrated 4 services to IaC → deploy time 45min → 8min\" |\n| Silently drop weak entries | Mark `(evidence needed)` and present for user to fill in |\n\n## Evidence Ladder\n\nNot every entry needs a metric. Use the strongest evidence available:\n\n| Strength | Evidence type | Example |\n|----------|--------------|---------|\n| ? Best | Quantified metric | \"Reduced P95 latency from 800ms to 120ms\" |\n| ? Strong | PR, commit, or doc link | \"PR #312, design doc in wiki\" |\n| ? Good | Observable outcome | \"Unblocked Team X\", \"Resolved Sev2 incident Y\" |\n| ✅ Acceptable | Qualitative + context | \"Reduced toil for on-call rotation — see updated runbook\" |\n| ⚠️ Weak | Activity only | \"Worked on auth\" — reframe or mark `(evidence needed)` |\n\nNever invent a metric to fill the gap. Qualitative evidence with context beats fabricated numbers.\n\n## Categories\n\n| ID | Emoji | Use for |\n|----|-------|---------|\n| `pr` | ? | Merged PRs, shipped features |\n| `bugfix` | ? | Bug fixes, incident patches |\n| `infrastructure` | ?️ | Infra, deployments, migrations |\n| `investigation` | ? | Root cause analysis, debugging |\n| `collaboration` | ? | Reviews, mentoring, design discussions |\n| `tooling` | ? | Dev tools, scripts, automation |\n| `oncall` | ? | Incident response, on-call wins |\n| `design` | ? | Design docs, architecture decisions |\n| `documentation` | ? | Docs, runbooks, guides |\n\n## How to Help the User\n\nFollow this decision tree:\n\n1. **If `save_to_brag_sheet` tool is available** → use extension tools directly (`save_to_brag_sheet`, `review_brag_sheet`, `generate_work_log`). Do not reference or attempt to call these tools unless they are confirmed available.\n\n2. **If git or gh CLI is available** → backfill from commits and PRs (see Backfill section below)\n\n3. **Otherwise** → guided interview: \"What did you work on?\", \"Who benefited?\", \"What's the evidence?\"\n\nFor each entry, walk through: **What** (the deliverable) → **Why** (who benefits) → **Evidence** (PR, metric, link). Output formatted markdown the user can paste into a review doc.\n\n## Backfill Workflow\n\nWhen the user asks \"what did I do last week\" or \"backfill my history\":\n\n**Follow these steps in order. Do not draft entries until scanning is complete.**\n\n### Step 1: Scan available sources\n\nCheck what's available, then mine each source:\n```bash\ngit --version 2>\u002Fdev\u002Fnull         # for commit mining\ngh --version 2>\u002Fdev\u002Fnull          # for PR mining\nls ~\u002F.copilot\u002Fsession-state\u002F 2>\u002Fdev\u002Fnull  # Copilot session logs\n```\n\n**Git commits** — recent commits by the user in the current repo:\n```bash\ngit log --author=\"$(git config user.email)\" --since=\"2 weeks ago\" \\\n  --pretty=format:'%h|%ad|%s' --date=short --no-merges\n```\n\n**PR history** — merged PRs across repos:\n```bash\ngh pr list --author @me --state merged --limit 20 \\\n  --json number,title,repository,mergedAt\n```\n\n**Copilot session history** (unique to this skill):\n- Path: `~\u002F.copilot\u002Fsession-state\u002F\u003Csession-id>\u002Fworkspace.yaml`\n- Read fields: `summary`, `cwd`, `repository`, `branch`\n- Skip sessions without a `summary` field\n- Note: this directory may not exist on all machines\n\nIf none of these sources are available, fall back to the guided interview.\n\n### Step 2: Group related work\n\nCluster related signals into one entry:\n- Same PR + its commits → 1 entry\n- Multiple commits on the same file\u002Ffeature within 3 days → 1 entry\n- Copilot sessions referencing the same repo + branch → merge into PR entry if one exists\n\n### Step 3: Draft entries\n\nWrite impact-first entries for each group. Assign categories.\n\n### Step 4: Present and refine\n\nShow all drafted entries to the user. Adjust based on feedback.\n\n### Step 5: Output\n\nFormat as markdown grouped by week:\n\n```markdown\n## Week of 2025-04-14\n\n### ? PRs & Features\n- **Migrated auth service to managed identity** → eliminated 3 secret rotation incidents\u002Fquarter → PR #312\n\n### ?️ Infrastructure\n- **Built CI pipeline for copilot-brag-sheet** → 107 tests across 3 OSes × 3 Node versions → shipped v1.0.0\n```\n\n## Performance Review Prep\n\nWhen the user is preparing for a performance review (Connect, annual review, etc.):\n\n### Structure\n\n1. **Gather** — collect entries from the work log (or backfill using the workflow above)\n2. **Select** — pick the top 3–5 highest-impact items\n3. **Rewrite** each item with three parts:\n   - **What I did** — the specific action\n   - **Why it mattered** — who benefited, what changed\n   - **Proof** — PR number, metric delta, dashboard link, customer outcome\n4. **Organize** by impact theme (not chronologically):\n   - Delivering results \u002F operational excellence\n   - Customer \u002F team impact\n   - Collaboration \u002F mentoring \u002F leadership\n   - Growth \u002F learning\n5. **Ask for gaps** — if evidence is missing, prompt the user: \"What metric changed?\", \"Who was unblocked?\", \"What's the PR or incident ID?\"\n\n### Strong vs weak entries\n\n| ✅ Strong | ❌ Weak |\n|----------|--------|\n| Outcome-first, quantified | Activity list (\"worked on X\") |\n| Tied to customer\u002Fteam impact | No beneficiary mentioned |\n| Includes evidence (PR, metric) | No measurable result |\n| Shows ownership or leadership | Pure task completion |\n\n### Narrative format\n\nFor longer narrative sections, use STAR: **S**ituation → **T**ask → **A**ction → **R**esult.\n\nFor Microsoft employees using the Connect preset, frame entries around Core Priorities: delivering results, customer obsession, teamwork, and growth mindset.\n\n## Output Contract\n\nBefore finishing, ensure:\n1. Every entry has action → result → evidence (mark `(evidence needed)` if missing)\n2. No fabricated metrics — only user-provided or source-verified data\n3. Entries shown to user before saving\n4. Time range explicitly stated\n5. Output is pasteable markdown with categories assigned\n\n## Gotchas\n\n### No recent commits in the current repo\nThe user may work across multiple repos. Before concluding there's nothing to backfill:\n1. Ask if they want to scan a different repo or branch\n2. Check `gh pr list --author @me --state merged` for cross-repo PRs\n3. Fall back to the guided interview — not all impactful work leaves git traces (design docs, incident response, mentoring)\n\n### Review period doesn't match git history\nPerformance reviews often cover 6–12 months. Explicitly set the date range:\n```bash\ngit log --author=\"$(git config user.name)\" --since=\"2024-07-01\" --until=\"2025-01-01\" --oneline\n```\nPR history (`gh pr list --state merged`) is more reliable for long time ranges than commit logs.\n\n### User can't quantify impact\nNot every entry needs a number. See the Evidence Ladder above. Acceptable evidence includes PR links, \"unblocked Team X\", or qualitative outcomes with context. Never invent a metric to fill the gap.\n\n### Copilot session directory doesn't exist\n`~\u002F.copilot\u002Fsession-state\u002F` only exists if the user has run Copilot CLI sessions. Don't error — silently skip and note: \"No Copilot session history found; scanning git and PRs only.\"\n\n### \"brag\" might mean something else\nThe user might say \"brag about this feature to my team\" (a launch announcement, not a work entry). Confirm intent if ambiguous.\n\n### Pair programming or co-authored commits\nIf multiple authors appear on the same commits, ask: \"Should I credit this as your work, shared work, or skip it?\"\n\n## Automatic Session Tracking (Optional)\n\nFor automatic background tracking of every Copilot CLI session (files edited, PRs created, git actions), install the [copilot-brag-sheet](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcopilot-brag-sheet) extension. It adds `save_to_brag_sheet`, `review_brag_sheet`, and `generate_work_log` tools to every session.\n",{"name":5,"license":14,"metadata":48,"description":50,"argument-hint":51,"compatibility":52},{"version":49},"1.1","Turn vague \"what did I do?\" into evidence-backed impact statements for performance reviews, self-reviews, promotion packets, and weekly updates. Uniquely mines Copilot CLI session logs to reconstruct forgotten work, plus git commits and GitHub PRs. Enforces a 3-part impact contract (action → result → evidence). Works standalone with zero dependencies. Trigger for: \"brag\", \"log work\", \"what did I do\", \"backfill my work history\", \"performance review\", \"self-review\", \"self assessment\", \"write impact statement\", \"review prep\", \"promo packet\", \"promotion case\", \"weekly update\", \"status report\", \"accomplishments\", \"what did I ship\", \"I forgot to log my work\", \"summarize my work\", \"track my wins\", \"what should I highlight\", \"end of half\", \"career growth\", \"work journal\", or any request to document, summarize, or organize work accomplishments.\n","Optional: time range (\"last 2 weeks\", \"this half\"), category (\"infrastructure\"), \"backfill\", or \"review prep\"","Cross-platform (Windows, macOS, Linux). Works with any GitHub Copilot CLI session. Optional: git, gh CLI.","main","068c2486ccc0f8d200a3db4d21ec137064eda3b4","skills\u002Fbrag-sheet","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing","https:\u002F\u002Fgithub.com\u002FJiayiV","2026-08-25 16:30:52",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add JiayiV\u002Fquestion_mixing --skill brag-sheet",{"tool":65,"command":66},"bunx","bunx skills add JiayiV\u002Fquestion_mixing --skill brag-sheet",{"tool":68,"command":69},"pnpm","pnpm dlx skills add JiayiV\u002Fquestion_mixing --skill brag-sheet","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fbrag-sheet\u002FSKILL.md",true,[],[74,100,126,159,187,220],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":43},"01M6NN9PJS9NHWPDG4QP93BP8F","webmcpify","Make a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for \"webmcpify\", \"add WebMCP\", or \"expose app actions to AI agents\".","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fwebmcpify\u002FSKILL.md",[],[76,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99],"github","ai agents","web","notes","code","browser","https","actions","manifest","inventory","verify","tool","use","ready","unrelated","app","scope","for","webmcp",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":104,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":43},"01M6NN6KZE5RBN6NGHN2WXV1RE","vardoger-analyze","Use when the user asks to personalize the GitHub Copilot CLI assistant, adapt Copilot to their style, use vardoger, or analyze their Copilot CLI conversation history. Reads the local session directory at `~\u002F.copilot\u002Fsession-state\u002F`, extracts recurring preferences and conventions, and writes a fenced personalization block into `~\u002F.copilot\u002Fcopilot-instructions.md`. Runs entirely on the user's machine via the local `vardoger` CLI (`pipx install vardoger`); no network calls and no uploads. Triggers: 'personalize my copilot', 'analyze my copilot history', 'tailor copilot to me', 'run vardoger', 'update my copilot instructions from history', 'make copilot learn my style'.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fvardoger-analyze\u002FSKILL.md",[],[108,109,110,111,112,113,114,40,115,116,117,118,119,120,121,30,122,123,124,125],"vardoger analyze","analyze","directory","cli","github copilot","copilot","run","learn","network","my style","install","conversation","me","local","pipx","my","at","copilot instructions",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":140,"publishedAt":43},"01M6NN3CZGQP3XAJ04BM1NNYGT","transloadit-media-processing","Process media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS\u002FMP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, add subtitles, OCR documents, or run any media processing pipeline. Covers 86+ processing robots for file transformation at scale.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftransloadit-media-processing\u002FSKILL.md",[132,137],{"categoryNo":133,"categoryName":134,"taxonomyType":135,"taxonomyTypeDesc":136},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":138,"categoryName":139,"taxonomyType":135,"taxonomyTypeDesc":136},"01JBSEEDCAT000000000000023","Skill与智能体开发",[141,142,143,144,145,146,147,148,149,150,151,152,153,93,154,155,156,157,98,158],"transloadit media processing","Media","media processing","processing","MCP","mcp server","documents","subtitles","pipeline","ocr","Video","Audio","mp4","images","files","transformation","free","hls",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":168,"publishedAt":43},"01M6NN28E92F9GH4WFYQ2H1Y15","terraform-azurerm-set-diff-analyzer","Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes. Use when reviewing terraform plan output for Azure resources like Application Gateway, Load Balancer, Firewall, Front Door, NSG, and other resources with Set-type attributes that cause spurious diffs due to internal ordering changes.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fterraform-azurerm-set-diff-analyzer\u002FSKILL.md",[165],{"categoryNo":166,"categoryName":167,"taxonomyType":135,"taxonomyTypeDesc":136},"01JBSEEDCAT000000000000011","运维与部署",[169,170,171,172,173,174,175,176,177,93,178,179,180,181,182,183,184,185,186,98],"terraform","SET","terraform azurerm set diff analyzer","diff","analyzer","diffs","azure","gateway","firewall","only","resource changes","provider","resources","load balancer","attributes","front","load","balancer",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":202,"publishedAt":43},"01M6NN1QMH2TDYWTH3XY3N5XPV","technical-job-search","Use this skill when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV\u002Fresume, writing a cover letter, evaluating a job offer, or drafting a post-interview follow-up email. Do not activate for general career advice unrelated to an active job search action.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-job-search\u002FSKILL.md",[193,196,199],{"categoryNo":194,"categoryName":195,"taxonomyType":135,"taxonomyTypeDesc":136},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":197,"categoryName":198,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000036","内容创作者",{"categoryNo":200,"categoryName":201,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000038","人力资源",[203,204,205,206,207,208,209,210,109,211,93,212,213,214,215,216,217,218,98,219],"search","Job Search","technical job search","technical","writing","tasks","email","parsing","interview","up","engineer","general","activate","do","task","cv","letter",{"skillNo":221,"name":222,"nameZh":6,"description":223,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":224,"categories":225,"keywords":226,"publishedAt":43},"01M6NMZFA67XYS1GS09WT42235","steno-mode","Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says \"steno mode\", \"shorthand mode\", \"compressed responses\", \"token reduction\", \"brief structured output\", or invokes \u002Fsteno. Supports four compression levels: lite, brief, court, machine. Do not trigger for requests needing polished prose such as onboarding\u002Ftutorial content, stakeholder or customer-facing copy, or teaching-focused explanations.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fsteno-mode\u002FSKILL.md",[],[227,228,229,230,231,206,232,93,216,233,234,235,236,237,238,239,240,241,98,242],"steno mode","mode","customer","brief","first","tutorial","teaching","tokens","as","trigger","structured output","machine","output","court","requests","response compression"]