All authors
Claude Skills by jamestexas
github.com/jamestexas43 skills2 installs148 views
- Docs**Status:** Proposed **Date:** 2026-02-12 **Context:** When an agent explores a mache FUSE mount, every file read requires manual permission approval because the mount path is outside the agent's working directories.Votes: 0GitHub stars: 2
- Plans> **Revision:** 2026-07-30 third final fail-closed correction after live > Rosary-contract review. **Goal:** Deliver a portable per-session `park-work` skill that returns `safe_to_close=true` only after strict durable evidence folds to completed or parked and the exact receipt is written and read back. **Architecture:** `SKILL.md` owns orchestration and human-facing boundaries. `scripts/fold.py` owns typed protocol validation, the deterministic fold, caller-stable retry planning, repository b...Votes: 0GitHub stars: 2
- HudCapture a note, playbook, peer, or project-context update into the user's personal work HUD — a local markdown tree at $HUD_ROOT. Triggers on "jot this down", "remember this for <project>", "add a playbook for X", "note this peer/colleague", "update the context for <project>", or "lint the hud". The consolidation rule: this is the only place standalone notes go — never write a note file anywhere else.Votes: 0GitHub stars: 2
- Break GlassEmergency IAM elevation for oncall/debugging. Discovers GCP projects and guides through granting/revoking permissions.Votes: 0GitHub stars: 2
- Claim LedgerBefore opening a PR, enumerate every behavior it claims — stated, callers- unaffected, invariants-preserved — and tag each with the strongest evidence actually held: RAN, READ, or ASSUMED with a closed-set reason. Ship the ASSUMED residue in the PR description; log harness blockers durably. After review, reconcile each correctness comment against the ledger so misses are classified as harness / context / attention / lying-test with data, not vibes. Use when peers keep finding correctness bugs...Votes: 0GitHub stars: 2
- Contract Parity AuditUse when one interface/trait has multiple implementations that are assumed equivalent (storage backends, providers, transports), when several public surfaces (CLI/API/webhook/worker) expose the same verb, when bugs cluster as "works on X but not Y", or to scope a guardrail-parity fix before estimating it. Read-only behavioral-contract audit producing two matrices; narrower and cheaper than a full counterfactual-audit — often its follow-up.Votes: 0GitHub stars: 2
- Counterfactual AuditUse when asked whether a repo's architecture is still right — a counterfactual "how would this be designed today?" question, a suspicion of over/under-engineering or monolith-vs-split, recurring bug families that smell structural, or before committing to a major refactor. Read-only, evidence-first, multi-pass; "the current design is largely right" is a valid verdict. Works on any language/repo.Votes: 0GitHub stars: 2
- Design Doc ReviewReview a design doc for the decision it asks you to ratify — not the prose. Catches the expensive-to-reverse mistakes while they are still words: a problem stated as a solution, alternatives that were never really considered, a one-way door taken without noticing it is one, invariants that hold only on the happy path, a contract the design cannot actually keep, and success criteria you could never falsify. Weights scrutiny by reversibility × blast radius and hunts the highest-value target of ...Votes: 0GitHub stars: 2
- Diagram Gen EmergentGenerate a bottom-up diagram of actual code coupling from cross-references — what the code does, not what was intended. Use for structural PR review; pair with diagram-gen-spec for intended-vs-actual drift.Votes: 0GitHub stars: 2
- Diagram Gen SpecGenerate a top-down diagram of intended architecture from a mache schema file — what the PR proposes, not what the code does. Local reviewer context only; pair with diagram-gen-emergent for spec-vs-reality drift.Votes: 0GitHub stars: 2
- Doc TriageFind internal docs (not for external consumers), review against code reality, bead real items, archive stale files. Converts markdown debt into tracked beads.Votes: 0GitHub stars: 2
- Explain WorkReview a PR, ticket, or path and explain it so it sticks — mache/CODEOWNERS/ ticket context synthesized into a taught explanation, not a bare findings list. Own work gets onboarding framing; a peer's gets findings-teaching. Not for posting reviews (pr-review) or the reviewer-only pre-flight alone (review-prep). Local only.Votes: 0GitHub stars: 2
- Feature ImplResearch-first feature implementation workflow. Use when building new features or net-new code that should follow existing codebase patterns. Enforces pattern discovery before coding; dispatches to repo-specific standards skills for convention checks.Votes: 0GitHub stars: 2
- Finding TriageTriage a list of candidate findings — from a PR review, a self-audit, an adversarial agent, a counterfactual or parity audit — and decide which ones deserve to be raised. Two bars, both required: TRUE (the code really behaves that way, mechanism verified at a named line) and MATTERS (practically actionable against this change). Use when you are holding a findings list and are about to hand it to a human. Read-only judgment: it decides what to raise, it does not post and does not patch.Votes: 0GitHub stars: 2
- First Party AuditBefore writing glue, a wrapper, or a "small helper", audit whether the capability already exists first-party — in the binary, the codebase, or the platform — and whether existing glue bypasses a better first-party implementation. Use when adding shell/Taskfile/CI glue, when a helper feels trivially writable, or when the same logic seems to exist twice. Produces an inventory with receipts, not vibes.Votes: 0GitHub stars: 2
- HandoffCompact a session into a handoff at the work SEAM — where this session ends and the next resumes. Writes a rosary mailbox entry, bead comment, jj checkpoint, and /tmp view; `--resume` drains it next session. Use at the end of a task another session must continue, or to resume one — not a general summary.Votes: 0GitHub stars: 2
- ImplementDeterministic end-to-end implementation orchestrator. Use when building net-new code or a fix that should follow the full pipeline — decompose → research → TDD loop → self-review gate → structural review. Thin: it SEQUENCES existing skills (problem-decomposer/work-scope, feature-impl, superpowers/test-driven-development, self-audit, test-fidelity, taskfile-ci-parity, structural-pr-review) in a fixed order with rigid gates; it does not re-derive them. Mirror of structural-pr-review for the bui...Votes: 0GitHub stars: 2
- Jj StackTurn one dev branch into small, individually-reviewable stacked PRs that land on a feature branch (one final merge to main), using jujutsu (jj) colocated with git plus keyless commit signing. Use after pr-buckets decides the slice boundaries, or whenever a large or multi-PR ticket wants one branch you follow linearly, split into tiny PRs peers review. Captures the jj primitives (colocate, duplicate, split, bookmark, sign, push) and the parts jj does not give you by default — the signing-backe...Votes: 0GitHub stars: 2
- Linear Escalation TriageUse for Linear tickets assigned to you — oncall queue sweeps, aged P1/P2 escalations in Triage > 7 days, stale Todos needing cleanup, or an external escalation (Slack/support) surfacing a ticket needing a triaged reply.Votes: 0GitHub stars: 2
- Mache UsageStart or locate a running mache MCP server for a source path or .db file. Builds a .db from source if needed. Base skill used by diagram-gen-spec, diagram-gen-emergent, and review-prep. Returns port and session ID.Votes: 0GitHub stars: 2
- Park WorkCheck whether the current human-agent work episode is mechanically safe to close, park incomplete work behind a verified durable checkpoint and receipt, or inspect a previously parked episode before a fail-closed resume gate.Votes: 0GitHub stars: 2
- Pr BoardAnswers "how are my PRs?", "did I address the review?", "anything waiting on me?". Lectio-first via authored-PR activity (reviews/comments by others, excluding your own replies), falls back to gh for coverage gaps, joins to local worktrees, prints a board of what needs you. Read-only.Votes: 0GitHub stars: 2
- Pr BucketsGroup a body of in-progress work (a diff, a branch, a set of changes) into small, individually-reviewable PR buckets sized to a LoC threshold — one concern per bucket, in dependency order. The input to jj-stack. Use when one dev branch has grown past a review-friendly size and needs slicing into small PRs. Distinct from problem-decomposer, which decomposes an aspiration into dispatchable beads BEFORE code exists; pr-buckets slices code that already exists.Votes: 0GitHub stars: 2
- Pr Review KitSelf-contained playbook for rigorous PR review: state inspection, design-intent hunting, verification rules (cite sources, walk commits, verify artifacts), agent dispatch, falsifiable-matrix output, GitHub posting only with explicit authorization. Generic, sequential phases.Votes: 0GitHub stars: 2
- Pr ReviewGive or respond to PR reviews with structural awareness via mache. Review mode: review-prep diagrams + impact analysis, parallel analysis agents, one consolidated GitHub review. Respond mode: address reviewer comments.Votes: 0GitHub stars: 2
- Pr SuggestionPost a GitHub review comment as an applyable "suggested change" — a ```suggestion block the author commits with one click — and, first, decide whether a finding should be a suggestion at all. `gh` has no native support for inline comments or suggestions, so this drives the REST reviews API directly. Use when a finding is a small, literal edit to a line the PR already changed. It is deliberately the WRONG tool for structural, additive, or unchanged-context findings; the decision rule below tel...Votes: 0GitHub stars: 2
- Prior Art CartographerProduce cited, structured comparisons between a project and external systems solving adjacent problems; updates a prior-art matrix. Use for prior-art research or "are we reinventing X?" before committing to a design. Max 5 systems/invocation; no uncited claims.Votes: 0GitHub stars: 2
- Problem DecomposerDecompose an aspiration into dispatchable bead specs via 5-whys descent + a 7-property rubric. Use when starting new platform/capability/migration work that needs breaking down before agents can ship it, or to audit a backlog for orphan-dispatchable beads.Votes: 0GitHub stars: 2
- Readme RestructureRestructure a README for human skimmers and LLM ingestion — fixes frontloaded internals, moves the value prop into the first 200 tokens, generates a diff for review. Preserves content, reorders disclosure. Sub-skill of repo-seo-curator.Votes: 0GitHub stars: 2
- Repo Description PolishAudit and polish the GitHub repo description — the pitch shown in search results, previews, and embeds. Proposes a stronger one from README + signals; applies via gh repo edit after approval. Sub-skill of repo-seo-curator.Votes: 0GitHub stars: 2
- Repo Homepage SetAudit and set the GitHub repo homepage URL — the link on the repo card's "About" panel and every search result. Detects candidates from docs sites, registries, and demos; applies via gh repo edit after approval. Sub-skill of repo-seo-curator.Votes: 0GitHub stars: 2
- Repo Social PreviewAudit the GitHub OpenGraph social preview image shown when a repo URL is posted on HN/Twitter/Slack/Discord. Flags if missing, checks clarity at small sizes, suggests sources, reports manual upload steps. Sub-skill of repo-seo-curator.Votes: 0GitHub stars: 2
- Repo Topic TaggerAudit and apply GitHub topic tags for discoverability — proposes tags from code signals, deduplicates against current tags, applies via gh api after explicit approval. Sub-skill of repo-seo-curator.Votes: 0GitHub stars: 2
- Review PrepSynthesize a PR's spec-driven diagram, emergent diagram, and impact analysis into reviewer context: what's proposed vs. what the code does vs. blast radius of changed symbols. Local only, never posted to GitHub.Votes: 0GitHub stars: 2
- Review QueueFan out isolated, one-per-PR reviews across your queue (own context + worktree per PR, no cross-pollution), then synthesize one report. Pulls the queue from a review inbox (zen) or gh; posts nothing without per-PR authorization.Votes: 0GitHub stars: 2
- Self AuditPre-review self-audit of a PR branch: dead struct fields, rotting comments, duplicate types, scope drift — what a human catches but a compiler won't — then dispatches an adversarial agent for deeper design flaws. Use before tagging a reviewer, or after a self-directed refactor.Votes: 0GitHub stars: 2
- Structural Pr ReviewDeterministic PR-review chain with pluggable structural intelligence. Fetches the PR into an isolated worktree, gathers the PR's own context with scripts/pr-context.sh, runs blast-radius/impact analysis through whatever code-intelligence tool is available (a depgraph tool like modmap, or an MCP server like mache), applies the pr-review-kit discipline, sweeps the review dimensions, drills findings to method granularity, gates them through finding-triage, teaches the result via explain-work, an...Votes: 0GitHub stars: 2
- SurveyMulti-perspective codebase survey that produces beads and mermaid diagrams from code structure. Each agent perspective (prod, staging, dev, feature, PM) examines the same codebase at a different zoom level, creating tagged beads and a disagreement matrix.Votes: 0GitHub stars: 2
- Taskfile Ci ParityWire validation so local == CI by construction: every check is a Taskfile target; CI and hooks invoke it rather than reimplementing it. Use when adding a validation gate, when local/CI disagree, or when a hook duplicates a command.Votes: 0GitHub stars: 2
- Test FidelityHunt vacuous / low-fidelity tests — the ones that pass whether or not the code is wrong in the way they claim to catch. Probes four shapes: a double that dodges the real thing, an assertion too loose to constrain behavior, inputs that never reach the claim, and coverage that is claimed but not guaranteed. Uses mache/modmap for value-origin and branch-reachability evidence and dispatches an adversarial agent for judgment. Use on a test-bearing PR or diff before review, or when a suite "passes"...Votes: 0GitHub stars: 2
- Work ScopeDecompose feature work into reviewable, shippable PR-sized units before coding starts. Use for a ticket, a feature description, or before a multi-file change. Feeds writing-plans — each unit becomes a plan.Votes: 0GitHub stars: 2
- Workflow AuditMine the user's Claude Code chat corpus for self-optimization patterns — repeated corrections, tool thrash, dropped threads — into a ranked, PII-scrubbed report. Different from self-audit (PR code review). Dispatch as a sub-agent to keep context clean.Votes: 0GitHub stars: 2
- Writing Pr DescriptionsUse when creating or updating a pull request description or body — opening a PR, or when a PR body is a raw template, a bot/scanner/generated dump, or a wall of headings a reviewer must read through.Votes: 0GitHub stars: 2