Concise skills rollout: docs-hygiene (10 skills, 9 model-invoked) #6554

Activity

1. kyle-sexton

   added a parent issue on Oct 7, 2026

   • Concise skills: one skill-creation standard, evals, and a fleet-wide rollout #6476
2. github-actions

   added

   needs-triageNot yet classified. Floor until a type and one priority tier are set.Not yet classified. Floor until a type and one priority tier are set.

   on Oct 7, 2026
3. github-actions commented on Oct 7, 2026

   

   github-actionsBot

   on Oct 7, 2026 – with GitHub Actions

   Last edited by melodic-automation-lanes

   Contributor

   More actions

   Proposed work class: work-class: scoped
   Basis: automated intake triage; the lanes App applied this class.

   Size: Large
   Complexity: Medium
   Uncertainty: Knowable
   Flags: none
   Blocked by: none

   Understood: one draft PR that rewrites the ten docs-hygiene skills to the skill criteria, following the playbooks rewrite-a-plugin runbook. It needs a per-skill decision table, and every shipped description and body change needs a measured eval pass. Any unmeasured skill gets named in the PR with its reason. The agent definition stays unchanged unless the #6476 agent pilot has landed.

   Nothing is missing, and I found no likely duplicates. The eval runs use the subscription login. They can't run in the issue lane, so an eval session has to run them.

   _{Automated triage, applied by the lanes App.}
4. github-actions

   added

   priority: mediumReal value, no hard deadline; normal backlog flow.Real value, no hard deadline; normal backlog flow.

   on Oct 7, 2026
5. kyle-sexton

   removed

   needs-triageNot yet classified. Floor until a type and one priority tier are set.Not yet classified. Floor until a type and one priority tier are set.

   on Oct 12, 2026
6. kyle-sexton

   added the

   Task

   issue type on Oct 12, 2026
7. kyle-sexton

   added

   needs-humanHuman-in-the-loop required; autonomous sessions must not resolve items carrying this.Human-in-the-loop required; autonomous sessions must not resolve items carrying this.

   on Oct 19, 2026
8. kyle-sexton commented on Oct 19, 2026

   

   kyle-sexton

   on Oct 19, 2026

   MemberAuthor

   More actions

   This was generated by AI during triage.

   Hold: the owner decision on #6476 (2026-10-18) puts this plugin in batch 2, which runs in a dedicated attended eval session, two plugins at a time, under a per-pass cost ceiling. It is not work for an unattended lane.
9. kyle-sexton commented on Oct 22, 2026

   

   kyle-sexton

   on Oct 22, 2026

   MemberAuthor

   More actions

   Parked (owner decision 2026-10-21): no eval spend until #7719 resumes hardening. This stays open and resumes then.
10. kyle-sexton

    removed

    needs-humanHuman-in-the-loop required; autonomous sessions must not resolve items carrying this.Human-in-the-loop required; autonomous sessions must not resolve items carrying this.

    on Oct 25, 2026
11. github-actions

    added

    needs-triageNot yet classified. Floor until a type and one priority tier are set.Not yet classified. Floor until a type and one priority tier are set.

    and removed

    needs-triageNot yet classified. Floor until a type and one priority tier are set.Not yet classified. Floor until a type and one priority tier are set.

    on Oct 25, 2026
12. melodic-automation-lanes

    added

    status: readyTriaged, unblocked, and fully specified; eligible to pick up.Triaged, unblocked, and fully specified; eligible to pick up.

    work-class: scopedA briefed fix or small feature; blast radius bounded by the brief, tests exist.A briefed fix or small feature; blast radius bounded by the brief, tests exist.

    status: needs-decisionAwaiting a human or maintainer judgment call.Awaiting a human or maintainer judgment call.

    on Oct 25, 2026
13. melodic-automation-lanes commented on Oct 25, 2026

    

    melodic-automation-lanesBot

    on Oct 25, 2026

    Last edited by melodic-automation-lanes

    Contributor

    More actions

    Not admitted to the issue lane yet: Size large: the split into sub-issues at intake is pending (owner Q93).
14. melodic-automation-lanes

    removed

    status: readyTriaged, unblocked, and fully specified; eligible to pick up.Triaged, unblocked, and fully specified; eligible to pick up.

    on Oct 25, 2026
15. melodic-automation-lanes commented on Oct 25, 2026

    

    melodic-automation-lanesBot

    on Oct 25, 2026

    Last edited by melodic-automation-lanes

    Contributor

    More actions

    The latest triage verdict holds nothing: the issue is at status: ready.
16. melodic-automation-lanes commented on Oct 25, 2026

    

    melodic-automation-lanesBot

    on Oct 25, 2026

    Contributor

    More actions

    Refinement. A read-only run explored this repository, searched its issues and pull requests, and read the allowed docs to draft what follows. On an issue a listed human filed, it counts as the issue's spec once posted, while unedited; it is still model text, so check it.

    Intended outcome: All 10 docs-hygiene skills are rewritten to the skill criteria in one draft PR with a per-skill decision table and measured descriptions and bodies.

    Dependencies

    • #​6476 umbrella: batch 2 runs in an attended eval session, per its 2026-10-18 owner decision
    • #​7719: owner parked eval spend until hardening resumes (2026-10-21)

    Related work

    • feat(code-tidying): concise skill text measured by evals, plus outcome cases for five skills #6539 (related): Merged-style precedent PR for a plugin rewrite (code-tidying); closed, not a duplicate.
    • feat(harness-ops): concise skill text measured by evals, plus outcome cases and probes #7434 (related): Precedent PR for a plugin rewrite (harness-ops).

    Open questions

    1. Should this issue stay held until #​7719 resumes hardening and the owner approves the /evals:plugin-eval spend, rather than being picked up by an unattended lane?
       RECOMMENDED: Yes, keep it parked and out of the unattended lane until both happen. Basis: Owner comments of 2026-10-19 and 2026-10-22 on this issue
    2. Should the body gain a task list of checkable criteria, such as a decision-table row per skill and named unmeasured skills, so the issue can be admitted once it is unparked?
       RECOMMENDED: Yes. Add one item per skill (10), a decision-table item and an unmeasured-skills item, and move eval-spend approval and draft-PR review into the person-only items. Basis: judgment
    3. Is the docs-hygiene agent definition in scope for this pass?
       RECOMMENDED: No. Exclude it unless the umbrella's agent pilot has landed. Basis: Issue body, 'The plugin today' section

    Sources read

    • plugins/docs-hygiene/skills/*/SKILL.md: the plugin has 10 skills (audit-derivability, audit-encapsulation, audit-noise, audit-progressive-disclosure, compress, extract-ssot, rename-references, setup, write-for-agents, write-for-humans), matching the issue body

    _{Automated refinement by the lanes App. Answer with a comment whose first line is **Decision recorded.**.}
17. kyle-sexton commented on Oct 25, 2026

    

    kyle-sexton

    on Oct 25, 2026

    MemberAuthor

    More actions

    Unparked by the owner's HITL session (2026-10-24): the owner's rule is that nothing stays parked unless it is unclear intent, a changed direction, a high security risk or an induced cost, and this hold was none of those.

    The runs use the eval lane's MAINTENANCE role (.github/lane-funding.json, role maintenance: keyed: false, MAINTENANCE_CLAUDE_CODE_OAUTH_TOKEN, a flat-fee subscription) or a local run on the operator machine's subscription; neither charges an auto-renewing key or a metered bill. The issue lane cannot run evals, so this goes to the eval session, not the lane.
18. kyle-sexton commented on Oct 26, 2026

    

    kyle-sexton

    on Oct 26, 2026

    MemberAuthor

    More actions

    This was generated by AI.

    Releasing the hold: no owner question is open. The refinement asked about eval spend or who runs the eval. Owner rules settle both. Evals run on the subscription login or not at all, never with an API key, and none start while the rate limit is near (Q110). Subscription and prepaid spend are not induced cost (Q46, Q91). Under the owner's 2026-10-26 stop rule (C14), an eval or host run is no longer an owner step, so an agent session runs it. The label comes off and intake triage runs again. Criteria:

    • One PR rewrites the docs-hygiene skills to the skill criteria per plugins/playbooks/skills/skill-authoring/reference/rewrite-a-plugin.md, with a per-skill decision table in its body.
    • Every shipped description and body change is backed by a valid /evals:plugin-eval measured pass run on the subscription.
    • Any skill left unmeasured is named in the PR with its reason.
    • The agent definition is unchanged unless the Concise skills: one skill-creation standard, evals, and a fleet-wide rollout #6476 agent pilot has landed.
19. kyle-sexton

    removed

    status: needs-decisionAwaiting a human or maintainer judgment call.Awaiting a human or maintainer judgment call.

    on Oct 26, 2026
20. github-actions commented on Oct 26, 2026

    

    github-actionsBot

    on Oct 26, 2026 – with GitHub Actions

    Contributor

    More actions

    The triage sweep dispatched intake triage for this issue (attempt 1 of 2).
21. melodic-automation-lanes

    added

    status: readyTriaged, unblocked, and fully specified; eligible to pick up.Triaged, unblocked, and fully specified; eligible to pick up.

    on Oct 26, 2026
22. kyle-sexton commented on Oct 28, 2026

    

    kyle-sexton

    on Oct 28, 2026

    MemberAuthor

    More actions

    Re-triage.

    This was generated by AI.

    This answers the three questions in intake's refinement (#6554 (comment)) and restates the criteria from #6554 (comment).

    1. Does this stay held until pr-pipeline: hardening deferred until the automated drain is proven #7719 resumes hardening and the owner approves the spend?
       No. The owner's session lifted the park on 2026-10-24 (comment of 2026-10-25). Newer owner rules settle the spend:
       • Q110: evals run on the subscription login or not at all.
       • Q91: subscription spend is not a cost stop.
       • C14: an eval run is agent work, routed to a session that can make it.
         The issue lane cannot make the measured eval passes, so this issue carries host-run and a host session takes it.
    2. Should the body gain checkable criteria?
       Yes. They are below.
    3. Is the docs-hygiene agent definition in scope?
       No, unless the Concise skills: one skill-creation standard, evals, and a fleet-wide rollout #6476 agent pilot has landed. The body says so in "The plugin today".

    The rewrite stays one pull request, as the body and the runbook ask.

    Acceptance criteria

    • One PR rewrites the docs-hygiene skills to the skill criteria per plugins/playbooks/skills/skill-authoring/reference/rewrite-a-plugin.md, with a per-skill decision table in its body.
    • Every shipped description and body change is backed by a valid /evals:plugin-eval measured pass on the subscription login.
    • Any skill left unmeasured is named in the PR with its reason.
    • The agent definition is unchanged unless the Concise skills: one skill-creation standard, evals, and a fleet-wide rollout #6476 agent pilot has landed.
23. kyle-sexton

    added

    host-runNeeds an unattended run on a host; the host runner takes it, not a person or the issue lane.Needs an unattended run on a host; the host runner takes it, not a person or the issue lane.

    on Oct 28, 2026
24. kyle-sexton

    self-assigned this

    on Oct 31, 2026
25. kyle-sexton commented on Oct 31, 2026

    

    kyle-sexton

    on Oct 31, 2026

    Last edited by kyle-sexton

    MemberAuthor

    More actions

    No description provided.
26. kyle-sexton

    added a commit that references this issue on Oct 31, 2026

    refactor(docs-hygiene): concise skill bodies

    ...

    b21c922
27. kyle-sexton

    closed this as completedin #11717on Oct 31, 2026