all publishers

MrBinnacle

@mrbinnacle source repo

44 published skills

  1. ▌
    Azimuth · mrbinnacle bundle
    Decision-quality pre-commitment analysis for initiative-level go/no-go calls with meaningful downside and limited reversibility — launches, rewrites, key hires, partnerships, strategic bets, timelines. Invoke when the user explicitly asks to pressure test, validate, or evaluate such a decision (e.g. 'should we do this,' 'pressure test,' 'go/no-go,' 'are we ready'). Do NOT invoke for routine code review, sub-task planning, reversible tactical choices, or pure ideation.
    1 repo stars
  2. ▌
    Gap Scanner · mrbinnacle
    Audits AZIMUTH's coverage completeness. Cross-references what SKILL.md claims to handle against what reference, diagnostic, and domain-policy files actually cover. Identifies thin coverage, missing domains, and structural inconsistencies. Run before major version planning.
    1 repo stars
  3. ▌
    Research Scout · mrbinnacle bundle
    Tracks AZIMUTH's 8 primary citation source families for new publications or significant updates. Stages validated findings in research/staged-findings.md for human review before promotion to references/base-rates.md. Invoke with 'run the research scout' or 'promote staged findings'.
    1 repo stars
  4. ▌
    Verdict Auditor · mrbinnacle
    Stress-tests an AZIMUTH output against the skill's own structural rules. Paste an AZIMUTH output and invoke to get a severity-rated diagnostic. Diagnoses only — does not rewrite. Use after any real AZIMUTH session to detect quality drift.
    1 repo stars
  5. ▌
    Reference Authoring · mrbinnacle
    Authoring discipline for new AZIMUTH reference files and templates. Use when adding a new domain reference file, extending an existing one, or creating a new template. Covers: (1) EXTEND vs. CREATE decision heuristic, (2) the Module 7 vocabulary header pattern that prevents domain-gap recurrence, (3) the sourcing caveat pattern for narrow-evidence-base files, (4) pre-verdict gate structure for templates. Validated by research-mpbaese4 (2026-05-18).
    1 repo stars
  6. ▌
    Brief Ids · mrbinnacle
    Use when flattening findings from several reviewers or seats into one brief or punch list. Their reviewer-local M1/M2/M3 ids collide at the consolidation layer and one finding is dropped silently.
    1 repo stars
  7. ▌
    Cwd Drift · mrbinnacle
    Use when a verification grep returns no matches and you are about to call the tree clean. The Bash tool's cwd persists across calls, so a relative path searches the wrong tree and reports zero.
    1 repo stars
  8. ▌
    Write Site · mrbinnacle
    Use when a reader greps an error, log or status message to decide severity, retryability or control flow. The site that knew the facts recorded only prose. Record them as a value, delete the match.
    1 repo stars
  9. ▌
    Uniform Eol · mrbinnacle bundle
    Use when a small edit produces a diffstat near the file's whole line count, or before writing a file with write_text on Windows. A uniform EOL conversion is invisible to a mixed-endings guard.
    1 repo stars
  10. ▌
    Blocked Form · mrbinnacle bundle
    Use when a guard, hook or sandbox refuses a destructive command and you are about to record the action as blocked, escalate it, or leave a ticket waiting. Read the refusal text first.
    1 repo stars
  11. ▌
    Worktree Cwd · mrbinnacle
    Use when ExitWorktree refuses with a cwd-override error and the branch still needs merging. Merge by ref with git -C from inside the worktree; a merge needs no navigation.
    1 repo stars
  12. ▌
    Im Up · mrbinnacle bundle
    Use when a fresh Claude Code session must resume from an im-down packet and verify repository state before any work begins.
    1 repo stars
  13. ▌
    Frontend Slop · mrbinnacle bundle
    Use when writing a single-file HTML artifact or a deployable frontend that must clear security gates - safe DOM construction, a host allowlist, a content-security policy, no secret in the output.
    1 repo stars
  14. ▌
    Honesty First · mrbinnacle
    Use when a drift catch surfaces both an inaccurate doc and the engineering gap it hid. Ship the doc truth inline now; surface the engineering work as its own dispatch decision. Neither blocks.
    1 repo stars
  15. ▌
    Nameable Half · mrbinnacle bundle
    Use when writing or trusting a checkpoint band, handoff or packet that compresses a receipt. A summary reading "all X are P" where the source said "P or Q" keeps the half with the familiar name.
    1 repo stars
  16. ▌
    Steering Head · mrbinnacle
    Use when one private repo decides and audits for public repos it owns: before building an instrument, when writing a bare #N issue reference, or when an artifact's home repo is unclear.
    1 repo stars
  17. ▌
    Agent Snapshot · mrbinnacle
    Use when a subagent reports a tool as unavailable or an agent type as not found after you edited .claude/agents/ this same session. The registry is snapshotted at session start, so the fix is inert.
    1 repo stars
  18. ▌
    Detached Child · mrbinnacle
    Use when a self-test passes in a Linux container and fails on Windows with WinError 32 at TemporaryDirectory cleanup. A detached child inherited the tempdir as its cwd; fix the product, not the test.
    1 repo stars
  19. ▌
    Squash Absorbs · mrbinnacle
    Use before cutting a branch while git says you are ahead of origin, or when a PR lists commits you did not write and a known SHA has left the default branch. Squash absorbs the unpushed base.
    1 repo stars
  20. ▌
    Wrong Altitude · mrbinnacle bundle
    Fires after a prior-art sweep SUCCEEDS: its sources are applied docs, not the theory they instantiate; you are about to record 'no prior art'; or a name-grep of zero is becoming an absence claim.
    1 repo stars
  21. ▌
    Im Down · mrbinnacle bundle
    Use when you are ending a Claude Code work session and the next session must resume from a verified packet instead of from conversational memory.
    1 repo stars
  22. ▌
    Dead Predicate · mrbinnacle bundle
    A router rule can be live, healthy and match nothing anyone types: the pattern list omits the ordinary word, or a JSON escape left the pattern inert. Use before claiming a discipline is hook-enforced.
    1 repo stars
  23. ▌
    Phantom Answers · mrbinnacle
    Use when a prompting script completes with nobody typing, writes blanks or defaults, or is about to run through a harness, pipe or CI. Without a TTY, read returns EOF rather than an error.
    1 repo stars
  24. ▌
    Shared Checkout · mrbinnacle
    Use before dispatching more than one agent that runs git in the same repo, or when a commit or rebase lands on a branch nobody targeted. They share one HEAD, which a file-overlap check cannot see.
    1 repo stars
  25. ▌
    Walk The Recipe · mrbinnacle
    Use when validating a README recipe, install script, onboarding or deploy doc written by someone whose machine already had everything. Walk every step in the target user's environment, not your own.
    1 repo stars
  26. ▌
    Reviewer Horizon · mrbinnacle bundle
    Use when assembling a brief for a reviewer or subagent, or when its answer collides with a rule you never sent. Your selection became its design boundary, so the collision is manufactured, not found.
    1 repo stars
  27. ▌
    Equivalent Mutant · mrbinnacle
    Use when a surviving mutant looks like a coverage gap but no falsifiable test can kill it in the current architecture. Re-classify it as equivalent; a test passing either way is the slop it hunts.
    1 repo stars
  28. ▌
    Prefill Rejection · mrbinnacle
    Use when an OpenRouter run dies on "does not support assistant message prefill", intermittently, or after a provider pin appeared to fix it. Pins cannot fix it and a green run proves nothing.
    1 repo stars
  29. ▌
    Linkcheck Throttle · mrbinnacle
    Use when a CI link checker reports 404 on github.com issue or PR URLs that gh api resolves fine. GitHub throttles anonymous page requests with 404, not 429, which reads exactly like a dead link.
    1 repo stars
  30. ▌
    Sdk Via Openrouter · mrbinnacle
    Use when ANTHROPIC_API_KEY is absent and OPENROUTER_API_KEY is present. Point the Anthropic SDK at openrouter.ai/api/v1 with a provider-prefixed model id; no other code changes.
    1 repo stars
  31. ▌
    Skill Reachability · mrbinnacle
    Use when a skill that is installed and working reports as missing, is refused by the Skill tool, or is absent from the listing. Three separate mechanisms produce that symptom; each has its own check.
    1 repo stars
  32. ▌
    Mocked Stub · mrbinnacle bundle
    A test that patches a helper which is itself a production stub reports green on a branch that never ran. Use when reviewing all-green tests on spend guards, idempotency, auth or refusal paths.
    1 repo stars
  33. ▌
    Pull Rebase · mrbinnacle bundle
    Use before `git pull` where `pull.rebase` may be `true`. `--no-ff` does NOT stop a rebase under `pull.rebase=true` (silently ignored); it rewrites every local commit SHA. Check config first.
    1 repo stars
  34. ▌
    Closure Mode · mrbinnacle bundle
    Closure-mode discipline at workflow boundaries. Use when a sprint, phase, or vertical slice locks clean, or when a multi-candidate "what next" decision arises. Owns the closure→build transition.
    1 repo stars
  35. ▌
    Stale Deploy · mrbinnacle bundle
    Verify a GitHub Pages (or any CDN-fronted) deploy actually serves new content. Poll on a marker that did not exist pre-deploy; avoid sleep-and-curl chains the agent harness blocks.
    1 repo stars
  36. ▌
    Clirunner Env · mrbinnacle bundle
    Click's CliRunner.invoke `env=` only overrides keys the dict names; an absent key is not deleted. Pass `{key: None}` to delete one. Use when a CLI test asserts on an env var being absent.
    1 repo stars
  37. ▌
    Vacuous Check · mrbinnacle bundle
    A success check accepting any non-empty output passes on failure, because failure output is non-empty too. Use when a script reports OK but nothing happened, or a probe says NOT-FOUND batch-wide.
    1 repo stars
  38. ▌
    Self Documenting Code · mrbinnacle bundle
    Use when reviewing code for clarity, refactoring names or flow without behavior changes, exposing units or side effects, or deciding which comments to keep.
    1 repo stars
  39. ▌
    Skill Family Curation · mrbinnacle
    Weeds a growing skill library: tests whether overlapping skills are one family using fixtures, then hands the human a disposition. Consolidation deletes child cards, so the human decides.
    1 repo stars
  40. ▌
    Pretooluse Prose · mrbinnacle bundle
    A PreToolUse Bash guard reads the whole command string, so it blocks prose that only mentions what it forbids. Use when a hook blocks its own install, or when writing a Bash matcher.
    1 repo stars
  41. ▌
    Decision Rights · mrbinnacle bundle
    Framing discipline for artifacts instructing a downstream reader — handoffs, plans, ADRs, subagent prompts. Separates evidence access from decision rights; marks which decisions evidence can reopen.
    1 repo stars
  42. ▌
    Halt As Deliverable · mrbinnacle bundle
    When a pre-registration, pre-flight or sanity gate refuses to produce your deliverable, the catch is often worth more than the deliverable. Use when a discipline you built caught your own work.
    1 repo stars
  43. ▌
    Subagent Handback · mrbinnacle bundle
    Pre-dispatch, name the return channel — a subagent handback can be empty. Verify tool grants match the task. Post-return, verify every claim, negatives first.
    1 repo stars
  44. ▌
    Disposition Schema · mrbinnacle bundle
    Use when dispatching parallel agents to verify/adjudicate findings — adversarial verify, security disposition, design triage, council fires. Shared disposition schema so seat outputs join cleanly.
    1 repo stars