flatnotes-tasksmd-github-audit
Thoroughly audit Tasks.md + Flatnotes for drift and accuracy; use GitHub (gh CLI) as source of truth to detect stale notes/cards and missing links. Produces a report and an optional fix plan.
- License 许可
- MIT
- 最近更新
- 2026-06-07
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- flatnotes-tasksmd-github-audit
- description
- Thoroughly audit Tasks.md + Flatnotes for drift and accuracy; use GitHub (gh CLI) as source of truth to detect stale notes/cards and missing links. Produces a report and an optional fix plan.
03 SKILL.md 正文
Flatnotes + Tasks.md + GitHub Audit
Use this skill when Brandon asks to audit the Flatnotes/Tasks.md system for accuracy and ensure it’s up to date, using GitHub as the source of truth.
Quick start
Run the bundled auditor (report-only):
node skills/flatnotes-tasksmd-github-audit/scripts/audit.mjs --since-days 30 --write
Outputs:
- Markdown report:
tmp/flatnotes-tasksmd-audit.md - JSON report:
tmp/flatnotes-tasksmd-audit.json
If
ghis not authenticated, the audit still runs but GitHub checks will be marked asSKIPPED_GITHUB.
Data sources (defaults)
- Tasks.md root:
/home/ds/.config/appdata/tasksmd/tasks - Flatnotes root:
/home/ds/.config/appdata/flatnotes/data - Flatnotes “system notes” mirror in workspace:
notes/resources/flatnotes-system/
Override via env vars:
TASKS_ROOTFLATNOTES_ROOT
Audit goals (what “accurate” means)
A) Board hygiene (Tasks.md)
- Global lanes exist:
00 Inbox,05 Backlog,10 Next,20 Doing,30 Blocked,40 Waiting,90 Done. - Lane rule preference:
prio-p2lives in05 Backlogby default (noprio-p2in10 Next). - Doing WIP ≤ 3 (preference).
- Cards should be consistently formatted (Outcome/Steps) and tagged (proj/prio/eff/type).
- Blocked cards include
Unblock:. - Project cards include a Flatnotes pointer (
Flatnotes: ...).
B) Project completeness (Flatnotes)
For each active project in SYS Workspace - Project Registry:
- Required project notes exist:
PJT <slug> - 00 OverviewPJT <slug> - 10 ResearchPJT <slug> - 20 PlanPJT <slug> - 90 Log
- Hub note has:
- Current status (1–3 bullets)
- Links section with repo + Tasks filter
- Decisions section linking relevant ADR(s)
C) GitHub truth reconciliation (GitHub = source of truth)
For each project repo in the registry:
- Open PRs should have a corresponding Tasks card (Doing/Next/Blocked/Waiting) OR an explicit reason why not.
- Recently merged PRs should be reflected somewhere:
- preferably a short note in the project log (
PJT <slug> - 90 Log) + hub status update, or - a Done card with PR link.
- (Audit treats either as reconciled; it may warn if a merged PR is only on a Done card but missing from the log.)
- preferably a short note in the project log (
- Done cards should ideally include a PR link when work was shipped via PR.
Workflow (recommended)
-
Parse registry
- Read
SYS Workspace - Project Registryfrom Flatnotes. - Extract: slug, status, Tasks tag, GitHub repo URL.
- Read
-
Scan Tasks.md
- Index cards by lane and by
proj-*tag. - Flag lane rule violations (
prio-p2in Next, etc.). - Flag cards missing Flatnotes pointer.
- Index cards by lane and by
-
Scan Flatnotes
- Check required project notes exist.
- Check hub Decisions section links ADR notes.
-
GitHub cross-check
- Use
gh:gh pr list --state open --json ...gh pr list --state merged --search "merged:>=<date>" --json ...(or equivalent)
- Try to match PRs ↔ Tasks cards using:
- PR URL in card content
- PR number
- Title substring heuristic
- Use
-
Report
- Output: summary + per-project drift list + fix plan.
Applying fixes (guardrails)
Default is report-only.
If Brandon explicitly asks to apply fixes:
- Safe auto-fixes allowed:
- create missing Flatnotes notes (
10 Research, etc.) using existing templates - add missing ADR links to hub Decisions section
- move
prio-p2from Next → Backlog - add missing Flatnotes pointers to Tasks cards
- create missing Flatnotes notes (
- Anything that renames files or deletes content: ask first.
Bundled code
scripts/audit.mjs— generates the report (Markdown + JSON). If needed, patch it rather than rewriting.
04 同仓库更多 Skills
crowd-prompting
A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.
ceaser
Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).
ceaser-send
Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.
dilemm-ai
Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).
moldium
Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.
arxiv-paper-reviews
Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.