criteria-contract
Prepare and pin agreed executable acceptance criteria for a selected verify-work case. Observe negative controls before work and protect the pinned checker afterward.
- License 许可
- MIT
- 最近更新
- 2026-11-12
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- criteria-contract
- license
- MIT
- description
- Prepare and pin agreed executable acceptance criteria for a selected verify-work case. Observe negative controls before work and protect the pinned checker afterward.
02 资源文件 2
- 脚本scripts/criteria-index.sh4.5 KB
- 脚本scripts/scaffold-run.sh5.6 KB
03 SKILL.md 正文
Prepare an acceptance contract
Dependency of verify-work, not an automatic prerequisite for every task. The core owns authority and scope; use the existing task record for required agreement and decisions.
- Run
scripts/scaffold-run.sh --slug <slug> --root <workspace>to create the compatibility-format case. Existing cases are never overwritten. - Replace template criteria with testable statements and
check_cmdlines. Keep required human observations as WITNESS. Include at least two executable checks and more executable checks than human observations. - Run the generated checker and observe every executable criterion reject the applicable negative state/control. Exit 1 means criterion failure; exit 99 means a broken harness and does not count as a negative proof.
- After the required owner agreement, run
scripts/scaffold-run.sh --pin <slug> --root <workspace>. This records hashes of criteria and checker. Pinning is an integrity operation; a hash alone is not evidence of human authorization.
The .redgate/ path and ARM/TRACE manifest labels remain a compatibility data
format. No recursive round, budget or cadence policy follows from those labels.
After pinning, return the case path and negative-control evidence to the task
owner. Do not edit ratified artifacts during work. A requirement change needs
a new contract rather than a re-pin of the old one.
scripts/criteria-index.sh optionally indexes existing records as pointers.
It is not a required new record or proof that an old check is applicable now.
04 同仓库更多 Skills
wayfinder
Chart a multi-session effort as a labeled map of typed decision tickets (grilling / prototype / research / task) with explicit dependencies and an open frontier agents self-assign into. Plans; never executes. Use this skill whenever the user is working with wayfinder, and on phrases like "chart this effort", "break this into tickets", "what's the frontier", "plan across sessions", or "map out the dependencies for this work".
wave-research
Staged, adversarial research that tries to break a thesis before believing it: waves, checkpoints, falsifiable sub-claims, rival hypotheses, an ACH matrix, source-incentive tags and a verified final thesis. Also carries Workflow templates for a one-pass research-and-verify fan-out. Use to stress-test or vet a contested claim; not for quick lookups.
second-opinion
Offer-only validation pipeline for a verdict or recommendation. Use when the user asks to validate, verify, fact-check, or get a second opinion on a claim or recommendation — "are you sure", "double-check this", "second opinion". Batches fact-checking against sources, adds scoped advisor personas for the angles that need judgment, then re-emits the response grouped into verified, flagged, and conflict, with a mandatory validation delta. Requires a subagent-spawning tool; without one it must decline rather than simulate.
machine-voice
Compression rules for standalone machine-read artifacts the reader scans — agent traces, tool-call logs, status lines, progress updates, handoff notes, state dumps, config, schemas, reference cards, and structured data another agent parses. Applies three layers: lexical compression, markdown structure as navigation, and emojis as typed status markers. Reach for it when emitting one of those artifacts on its own. Companion to human-voice, which governs prose a human reads and also owns any table or block that serves surrounding explanation. Neither skill applies to code or file contents the user will save, commit messages, creative writing, or turns that are only a clarifying question — those ship unstyled and uncompressed.
human-voice
Style for prose a human reads — answers, recommendations, explanations, research summaries, comparisons. Use on every conversational reply that contains prose for a person to read: triage intent, lead with the verdict, keep it scannable, tag claim confidence. Reach for it whenever answering a technical question, comparing options, or making a recommendation, even when the user says nothing about style. Companion to machine-voice, which instead governs standalone machine-read artifacts — agent traces, tool-call logs, status lines, progress updates, handoff notes, state dumps, config, schemas, reference cards, and structured data another agent parses. Neither skill applies to code or file contents, commit messages, creative writing, or turns that are only a clarifying question — those ship unstyled.
ai-writing-mistakes
Catch and repair the tells that mark prose as machine-written — the negation-flip ("it's not X, it's Y"), rule-of-three padding, hedge stacking, unearned intensifiers, filler verbs like delve and leverage, participle trailers ("...ensuring seamless integration"), sycophantic openers, empty closing summaries, and uniform em-dash/sentence rhythm. Use when drafting or revising any prose a human will read, including documents you were asked to author — READMEs, docs, PR bodies, release notes, emails — and when the user asks whether something "sounds like AI" or wants writing tightened. This is a wording pass, not a voice: human-voice still decides layout and confidence tags, machine-voice still owns traces and logs, and neither this skill nor those two touch code, commit messages, or quoted text.