Claude Skills by jposluns

Draft, rewrite, edit, review, or quality-assure prose using the Clean Language standard. Use for emails, Teams or LinkedIn messages, executive communications, reports, policies, governance artefacts, technical documentation, incident communications, strategy material, and other finished prose where directness, precision, natural cadence, Oxford English, and removal of generic AI-writing patterns matter. Preserve legal, technical, contractual, quoted, and standards language when alteration cou...

Grounds explanations of why an external action cannot or will not proceed in a real tool result, not in inference. Use before writing any clause of the form "X is blocked / waiting on / requires / needs / would fail" attached to an external action you have not attempted this turn. Use when about to explain why a PR cannot merge, why CI is waiting, why a deploy is held, why a permission is missing, or why any external system step is not proceeding. The safe action is attempted before the expla...

Run-once onboarding for a fork of a project that ships this governance pack. A maintainer's clone carries accumulated operational working-state (audit-trail registers, session handoff, a queue of next actions, per-document review anchors) that is meaningless to a fresh adopter; this skill either resets present machinery-core working-state to clean adopter baselines or, when the configured working-state location is absent, treats it as already clean and creates only the adopter-local state a p...

Routes a change through the correct workflow when the change touches a generated artefact or a protected branch. Use before hand-editing a file that is produced by a generator (build outputs, schema dumps, taxonomies, doc portals, scorecards, lockfiles). Use before pushing directly to, force-pushing, or `reset --hard`ing a protected branch (the default branch, release branches, long-lived integration branches). Use when CI flags generated-artefact drift or a protected-branch operation. The wo...

Composes a CHANGELOG entry (substantive or terse form) for a PR. Use when about to commit, open a PR, or finalize a change. Every PR carries an entry, even if terse; there is no skip path. The entry's required parts (date-and-version header, structured Keep a Changelog sections for substantive entries, file references as markdown links, the "why" not just the "what", verification evidence, phase context) are walked step by step so an entry that would fail the link-coverage gate, the version-m...

Before any completion claim on a change that touches a document containing external-source citations (verbatim quotes, paraphrased synthesis, or framework references with article / section / clause locators), verify each citation's text against the cited source at the cited location. Catches the failure mode where a confidently-cited quote does not actually appear in the source, or a paraphrase mis-represents the source's meaning. Catches what the mechanical citation linters (format and curre...

Cadenced citation-precision audit of normative-attribution claims. Catches the gate-blind "attributed value, silent source" class: a sentence ties a specific value (a retention period, a clock, a threshold) to a named normative source, the source exists and the citation is well-formed (so the existence and citation gates pass), but the source does not actually prescribe the attributed value. Run the one-time full Tier-A pass at adoption, then ad-hoc when a claim is in doubt and after any batc...

Surfaces ambiguity in one sentence and asks before acting, rather than silently picking. Use when a request supports more than one reasonable interpretation, when an external value the request does not pin down is required, when a project-specific convention must be chosen, or when an unexpected state of the world is encountered.

Maintainer-invoked, rare-cadence whole-project deep assessment. Runs the full layered examination of the project and its quality machinery from a fresh session, composing the configured semantic instruments by invocation and adding the lenses the routine cadence does not apply to itself: gate-efficacy probing, ground-truth citation sampling, adoptability and pipeline-integrity review, and a QA-ledger meta-audit. Multi-session and re-entrant: a durable register carries phase state across sessi...

Trust-recovery deep quality-assurance pass. A six-subagent forensic review specialized for AI-failure-pattern classes, run over a defined PR window plus the files those PRs reference, when an AI coding assistant's discipline failures (abbreviated QA, skipped post-commit audits, wrong-cadence timers, inferred-not-validated premises) call for a white-box re-examination beyond the routine per-PR and periodic sweeps. Slash command `/full-qa`. Pairs with `library-fitness-review` (`/fitness`): deep...

Verifies completion claims with evidence before declaring done. Use before stating "done", "complete", "fixed", "shipped", "ready", or any synonym. Use when wrapping up a unit of work and about to summarize to the user. Use when about to acknowledge a user-reported issue with "good catch". Use also before asserting a factual property of an artefact you have not read (a state assertion in research, assessment, planning, or review), not only at completion. Also use before ending a turn on a sta...

Before declaring a new or substantively-revised governance document complete, dispatch a fresh subagent with no session context to read the document and surface tacit-context gaps (ambiguous terms, missing definitions, implicit assumptions, unresolved references that the author knows but did not write down). Catches the failure mode the author cannot catch directly: the "I know what I meant" blind spot that fills the document's gaps invisibly during authoring.

Diagnoses a failing CI gate, lint, or audit and fixes the artefact rather than weakening the gate. Use when a gate fails. Use when tempted to bypass a check with --no-verify, blanket suppression, severity-threshold lowering, or exemption-list addition. Use when a pre-commit hook blocks a commit. Use when a required status check on a PR shows red.

When the governance machinery itself (the rules, skills, and audit gates that keep a governed codebase honest, plus their wiring surfaces) needs a structural-integrity review, run this skill. It is the periodic guard-rail review: a judgment-based pass over the machinery for overlap (two rules or gates covering the same ground), gap (a stated discipline no gate enforces, a recurring failure mode no rule names), and drift (a rule, skill, or gate whose intent has diverged across its wiring surfa...

Run the heavier pre-apply verification harness for a SENSITIVE change, one that is gate-blind on correctness (a fit or semantic property no existence gate can check), delicate at scale (a wide reshape or bulk mapping where a hand-edit is itself a defect risk), and costly to get wrong (a cited or downstream-relied-on artefact). Use before applying such a change, when the maintainer directs absolute-integrity rechecking, or when resuming a sensitive item left open in the register. It composes r...

Trigger a comprehensive whole-collection library-fitness review with a project-defined catalogue of persona reviewers when a documentation collection (the parent case is a governance/security documentation library) undergoes a major change or reaches its minimum review cadence, quarterly by default unless the adopting project records a different interval. The parent GRC library's major-change triggers are a new domain directory, a new document type, multiple governance rule additions, and a m...

Cadenced semantic-fit audit of a compliance matrix and per-document framework-alignment tables. Catches the gate-blind "valid code, wrong control" class: a control identifier that EXISTS in its catalogue (so the existence gates pass it) but is the WRONG control for the row's document. Run after any batch that adds or edits mapping rows, once when a mapping surface reaches completion, and ad-hoc when a control-code citation is in doubt. It dispatches a semantic judge over the worklist the proj...

Per-PR process retrospective, run as a PR's finalizing step before merge. Surfaces what went well, what caused friction, recurring patterns, and proposed improvements. Output is one entry per PR in the improvement-log register; recurring patterns become candidates for pack-rule updates, worker-brief template additions, or new audit gates. Invoke after the PR-scoped validation sweep (`validation-sweep-pr-scoped`; the parent library's `/validate-pr`) returns and before the next-PR planning step.

Formal screening protocol for a project's configured untrusted-source collection, run before any untrusted source informs project work. Catches the trust-boundary class citation and currency gates cannot see: untrusted external material inside an AI's reference context can carry bias, factual error, prompt injection, or instruction smuggling. Run it on every new untrusted-source ingest, on the configured pending worklist, and ad-hoc before reliance. It combines a mechanical instruction-conten...

Cadenced reference-breadth audit between a project's content collection and its configured source store, in both directions. Catches the gate-blind "held but unused" class: an authoritative source is held while project documents it could materially improve never engage it, or a project document is touched while newly ingested or updated source material that bears on it goes unnoticed. Run it exhaustively, per touched project document, and per source ingest according to configured modes. It di...

When adding a new skill to the governance pack's `skills/` collection, or when substantively revising an existing skill's structure or frontmatter, apply the pack's established eight-section structural template (YAML frontmatter with `derives_from`, Overview, When-to-Use, Process, Red Flags, Verification, Common Rationalizations, See Also) and validate trigger-accuracy with representative positive, negative, and boundary prompts. Catches structural drift across pack skills that accumulates si...

Runs the stop-consider-confirm protocol when executing a clear instruction as given would be counterproductive. Use when an instruction would destroy or discard committed work, reduce quality or efficiency with no offsetting benefit, contradict a goal the requestor stated, or rest on an apparently stale belief about current state; and when a brief instruction has both a harmful literal reading and a sensible charitable one. Walks the trigger test, the charitable-interpretation and stale-state...

Validates an inferred premise with a concrete observation before an action depends on it. Use when a draft or plan contains "since / because / given X, do Y" where X is a state claim not observed this turn, when about to skip a step because a prior run covered it, when declaring a fix complete because the named occurrence is fixed, or when acting on remembered rather than re-read state. Walks the discipline (name the inference, cost the validation, validate with a tool call, act on the observ...

PR-scoped validation sweep. Runs as a PR's finalizing step, before merge, to catch issues the PR introduced before it lands. Dispatches Subagent A (recent-PR deep review) scoped to the PR's diff plus a lightweight cross-reference check for files cited by other documents. Complements the project-wide `validation-sweep` skill: the PR-scoped form is fast and runs on every PR; the project-wide form is comprehensive and runs on a periodic cadence the project sets (a small-team default in the tens ...

Project-wide regression sweep run as a follow-up after any issue is identified and corrected, to confirm no sibling issue remains anywhere in the repository. Invoke after fixes that touch multi-surface artefacts, gate inventories, prose claims about repository state, AI-inferred citations, or generated artefacts. Combines the mechanical audit suite with a structured semantic fan-out, and loops until clean.