CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

housekeeping

Run the recurring housekeeping pass — audit the agent files for rot, the glossary against the code, the decision index, the mutation measurement, the worktrees and the diary, then scan the codebase for Ousterhout's red flags and route each finding to the skill that owns it. It never fixes what it finds; findings leave as candidate tickets. Its one write of its own is stamping the diary's Last housekeeping row, and its one delegated action is the worktree pruning it hands to the cleanup skill. Use when the docs gate's housekeeping-due advisory fires, on the cadence the gate config names, or before cutting a release.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tightly written, well-structured instruction skill with concrete file paths, commands, output formats, and explicit boundaries, and it correctly defers detail to a reference file. Its main weaknesses are the missing CHECKLIST.md in the bundle (making the deferred per-item detail unreachable), an indirect reference to the mutation command, and some repeated emphasis that costs tokens.

Suggestions

Ship CHECKLIST.md alongside SKILL.md (or inline the per-item criteria — what to look at, what counts as a finding, where to route it) so the deferred detail in "The checklist" section is actually reachable from the bundle.

In checklist item 4, name the exact mutation-measurement command (or its resolution path) directly instead of dereferencing it through the engineering article's decision line, so the pass can run it without a document chase.

State the never-fix rule once in "What this skill does not do" and drop its re-statements in Routing, Procedure, and Anti-patterns to recover tokens without losing the invariant.

DimensionReasoningScore

Conciseness

The body is dense and operational — it assumes competence and explains only kit-specific invariants (e.g. the shared invariant §10 rationale for never fixing), but the rhetorical opening ("Standing instructions rot on a calendar, not on an event") and the ~4-fold restatement of the never-fix rule (description, "What this skill does not do", Routing, Procedure, Anti-patterns) could be trimmed. This lands at the 4 anchor (efficient, minor over-explanation) rather than the 5 anchor's every-token-earns-its-place.

4 / 5

Actionability

Concrete guidance is strong: named files (docs/diary.md, scripts/docs-conformance/config.mjs), a runnable command (sh scripts/agents.lib.sh planner), an exact report path pattern (<tmpdir>/housekeeping-<YYYYMMDDTHHMMSSZ>.md), the diary row template, and a commit-message convention. However, the per-item audit procedures are deferred to CHECKLIST.md, which is absent from the bundle, and item 4's mutation tool is named only via a dereference to the engineering article's decision line — minor gaps per the 4 anchor, not the 5 anchor's fully copy-paste-ready coverage.

4 / 5

Workflow Clarity

The Procedure section gives a clear 6-step sequence with pre-start state checks, an evidence-per-item requirement ("'Nothing found' is a per-item statement with what was checked"), and an explicit stop boundary, which approaches the 5 anchor. But the full form of each checklist item — what to look at, what counts as a finding, how to route it — lives in a CHECKLIST.md that is not present in the bundle, leaving minor validation/checkpoint gaps at the item level (4 anchor).

4 / 5

Progressive Disclosure

Sections are well organized (context, non-goals, pre-states, checklist, routing, procedure, anti-patterns) and the one reference is clearly signaled and one level deep ("The full form of each ... is in CHECKLIST.md"). But no references/, scripts/, or assets/ directories exist in the bundle, so the referenced CHECKLIST.md is a dangling path from the evaluator's standpoint — good structure with a minor organization gap (4 anchor) rather than the 5 anchor's verified, well-signaled references.

4 / 5

Total

16

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A highly specific, third-person description that clearly states both capability and explicit triggers, with well-scoped boundaries (never fixes; one diary write; one delegated pruning action). The only weakness is trigger coverage that assumes familiarity with this kit's internal vocabulary rather than including broader natural phrasings.

DimensionReasoningScore

Specificity

The description enumerates concrete audit actions ("audit the agent files for rot, the glossary against the code, the decision index, the mutation measurement, the worktrees and the diary, then scan the codebase for Ousterhout's red flags") and even scopes its write behavior ("Its one write of its own is stamping the diary's Last housekeeping row"). This matches the 5 anchor's comprehensive, multiple specific concrete actions; the 4 anchor would require minor coverage gaps, which are not evident.

5 / 5

Completeness

It explicitly answers both: what (the audit actions and the route-everything-never-fix behavior) and when ("Use when the docs gate's housekeeping-due advisory fires, on the cadence the gate config names, or before cutting a release"). Both are concrete and explicit, matching the 5 anchor; the 4 anchor's "when could be more explicit" does not apply.

5 / 5

Trigger Term Quality

Triggers like "housekeeping", "housekeeping-due advisory", "cadence", and "before cutting a release" are natural phrases for this kit's users, but coverage is niche and kit-internal with few synonyms or alternative phrasings a user might spontaneously say. Good but not comprehensive coverage per the 4 anchor; the 5 anchor would demand synonyms/variations comparable to "PDF files, PDFs, forms, .pdf".

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (a recurring, time-triggered audit pass that only routes findings) with distinct triggers tied to the docs gate advisory and release cadence, so overlap with repair or ticket-writing skills is minimal. This fits the 5 anchor's "clear niche with distinct triggers; minimal conflict risk" rather than the 4 anchor's minor-overlap case.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 2 possibly missing (scripts/agents.lib.sh, scripts/docs-conformance/config.mjs), 1 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository

agranado2k/tic-tac-toe-haskell

Path

.agents/skills/housekeeping/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.