CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

conversation-hygiene

Triage and archive accumulated Codex conversations without losing wanted work. Use when cleaning up old Codex threads, deciding which conversations still need attention, or resuming a large conversation cleanup. Do not use for ordinary backlog capture, feature implementation, or issue-tracker cleanup.

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

81%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 well-crafted process skill: dense actionable guidance, a clearly sequenced workflow with unusually strong validation and failure-handling for a batch operation, and clean organization. The only gaps are a few trimmable abstract statements and the absence of any worked example, plus a single-file structure that keeps everything inline.

DimensionReasoningScore

Conciseness

Dense, skill-specific policy prose with no padding of concepts Claude already knows — lines like "Archiving is reversible; it does not delete the task" carry real guidance. A few abstract or repeated statements (e.g., task/outcome lifecycle framing, approval rules restated across sections) could be trimmed, fitting anchor 4 rather than the every-token-earns-its-place bar of anchor 5.

4 / 5

Actionability

Concrete, executable instructions throughout: "Inventory IDs before archiving so pagination shifts cannot skip candidates", "recheck each authorized task for new activity", "Archive only authorized IDs... then verify each in archived-task state", plus an explicit four-branch decision procedure for outcomes. It falls short of anchor 5 only in lacking a worked example (e.g., a sample proposal or checkpoint format); it is well above the vague/pseudocode level of anchor 3.

4 / 5

Workflow Clarity

Clear four-stage sequence (Gather evidence → Account for each outcome → Propose → Execute and close) with pervasive explicit validation for this batch operation: "confirm the write succeeded", "Do not infer success from a mutation response alone", "If preservation fails, leave its source task unarchived", and feedback loops ("retry unconfirmed operations", rechecking tasks with new activity). The checkpoint field list and separate reporting counts act as checklists — anchor 5.

5 / 5

Progressive Disclosure

No bundle files exist, and the single file is well-organized into clear sections with one clearly signaled external reference ([backlog item](../../../BACKLOG.md#conventions)). However, at ~103 lines it exceeds the under-50-line simple-skill threshold, and all content is inline with nothing split out, fitting anchor 4 (good structure, minor organization gaps) rather than anchor 5.

4 / 5

Total

17

/

20

Passed

Description

87%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 strong description: concrete actions, explicit use/avoid triggers in third-person voice, and a well-delineated niche. Minor trigger-synonym and coverage gaps keep specificity and trigger quality at 4.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions — "Triage and archive accumulated Codex conversations without losing wanted work" — with minor gaps in coverage (the body's backlog-item creation, checkpointing, and proposal steps are not surfaced). It exceeds anchor 3's 1-2 actions but is not comprehensive enough for anchor 5.

4 / 5

Completeness

Explicitly answers both: what it does ("Triage and archive accumulated Codex conversations without losing wanted work") and when to use it via a concrete "Use when cleaning up old Codex threads, deciding which conversations still need attention, or resuming a large conversation cleanup" clause, plus negative triggers. This matches the anchor 5 pattern exactly.

5 / 5

Trigger Term Quality

Includes natural user phrases — "cleaning up old Codex threads", "resuming a large conversation cleanup" — and synonyms (conversations/threads). A few natural variations are missing (e.g., "archive old tasks", "close finished conversations"), so it fits anchor 4 rather than the comprehensive coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

"Codex conversations" pins a clear niche with distinct triggers, and the explicit "Do not use for ordinary backlog capture, feature implementation, or issue-tracker cleanup" clause delineates boundaries from adjacent skills, minimizing conflict risk — anchor 5.

5 / 5

Total

18

/

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

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

EpicenterHQ/epicenter

Path

.agents/skills/conversation-hygiene/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.