add-compact

Add /compact command for manual context compaction. Solves context rot in long sessions by forwarding the SDK's built-in /compact slash command. Main-group or trusted sender only.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/add-compact/SKILL.md

Quality

Content

88%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.

The body is highly actionable with a clear, well-validated workflow and good structure. Minor conciseness and progressive-disclosure gains are available by tightening or externalizing the lengthy verification checklist.

Dimension	Reasoning	Score
Conciseness	Efficient and free of concept over-explanation; the 16-step verification checklist is thorough but slightly longer than strictly necessary and could be trimmed.	4 / 5
Actionability	Fully executable, copy-paste-ready commands throughout (test -f, git fetch/merge, npm test, npm run build, ./container/build.sh, launchctl kickstart) with concrete verification actions.	5 / 5
Workflow Clarity	Clear phased sequence (Pre-flight → Apply → Verify) with explicit validation checkpoints (npm test, build, container rebuild) and feedback loops documented in Troubleshooting.	5 / 5
Progressive Disclosure	Well-organized into clear sections with a one-level repo reference (docs/SECURITY.md); the long inline verification checklist is the only structural gap that could be split out.	4 / 5
	Total	18 / 20 Passed

Description

70%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.

The description is specific, concrete, and well-differentiated, but it lacks an explicit 'Use when…' trigger clause, which caps completeness. Adding explicit usage guidance would bring it to the top tier.

Suggestions

Add an explicit 'Use when…' clause naming concrete triggers, e.g. 'Use when the user wants to manually compact/summarize conversation context in a long-running session.'

Include natural synonyms users might say (e.g. 'summarize conversation', 'free up context') alongside 'context rot' and '/compact' to broaden trigger coverage.

Consider stating the intended environment briefly (e.g. 'for the NanoClaw agent runner') to further sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Add /compact command', 'forwarding the SDK's built-in /compact slash command') plus a concrete access constraint ('Main-group or trusted sender only'), with only minor coverage gaps.	4 / 5
Completeness	The 'what' is clear, but the 'when' is only weakly implied ('long sessions') with no explicit 'Use when…' trigger guidance, capping completeness per the rubric guideline.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('/compact', 'context compaction', 'context rot') but lacks synonyms like 'summarize conversation' or 'clear context'.	4 / 5
Distinctiveness Conflict Risk	A clear niche (manual context compaction via the SDK's /compact) with a distinct trigger and minimal overlap with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: jbaruch/nanoclaw-telegram
Path: .claude/skills/add-compact/SKILL.md
Commit: 7454673

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.