cc-skill-continuous-learning

Turn a completed debugging session or repeated user correction into a small, evidence-backed procedure. Use for explicit requests to capture reusable lessons; does not automatically extract or save memories.

Quality

68%

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 ./skills/cc-skill-continuous-learning/SKILL.md

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.

The content is a lean, well-structured instruction skill with concrete steps, a useful worked example, and clear guardrails against automatic memory mutation. Its main gaps are the absence of the referenced bundle script and the lack of an explicit validation feedback loop.

Suggestions

Add the referenced evaluate-session.sh to a bundled scripts/ directory (or remove the reference) so the linked helper is real.

Include a minimal reusable template for the output procedure (Trigger / Prerequisites / Steps / Verify / Expected / Limit) to make step 4 fully copy-paste ready.

Add an explicit validate-fix-retry note (e.g. re-run the reproduction after edits and only save when it passes) to strengthen the workflow's feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence, with tight sections like the 7-step Procedure and a compact worked example; a few explanatory sentences in Limitations and the worked-example preamble could be trimmed.	4 / 5
Actionability	Guidance is mostly executable: a concrete 7-step procedure, a worked example with explicit Trigger/Prerequisites/Verify/Expected/Limit fields, and a copy-paste bash command for the helper, with only minor gaps (e.g. no template for the final procedure artifact).	4 / 5
Workflow Clarity	The Procedure is a clearly numbered sequence with checkpoints (verify the fix in step 2, compare with existing instructions in step 6, read back the saved result in step 7), and guardrails prevent automatic saving, though there is no explicit validate-fix-retry feedback loop.	4 / 5
Progressive Disclosure	Sections are well-organized with clearly signaled, one-level-deep references to evaluate-session.sh and config.json, but the referenced helper script is not actually present in a bundled scripts/ directory, a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

62%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 clearly states what the skill does and when to use it, with a useful negative boundary that reduces conflict risk. It is somewhat under-specified on the range of concrete actions and could use a broader set of natural trigger phrases.

Suggestions

Add 1-2 more concrete actions (e.g. 'draft a runbook', 'compare against existing project notes') to broaden capability coverage.

Expand trigger phrases with synonyms users actually say, such as 'save what I learned', 'write a runbook from this session', or 'turn this fix into a reusable checklist'.

Consider adding a brief 'do not use for' clause (e.g. one-off typos, unresolved guesses) to sharpen the trigger further.

Dimension	Reasoning	Score
Specificity	It names the domain ('completed debugging session or repeated user correction') and one concrete action ('Turn ... into a small, evidence-backed procedure'), but does not enumerate multiple specific actions, so it falls short of comprehensive coverage.	3 / 5
Completeness	Both 'what' ('Turn a completed debugging session ... into a small, evidence-backed procedure') and 'when' ('Use for explicit requests to capture reusable lessons') are present, though the 'when' clause could name a few more concrete trigger phrases to reach explicit full coverage.	4 / 5
Trigger Term Quality	Relevant natural terms like 'debugging session', 'repeated user correction', and 'capture reusable lessons' appear, but common synonyms and variations a user might say (e.g. 'save what I learned', 'write a runbook') are missing.	3 / 5
Distinctiveness Conflict Risk	The niche (evidence-backed procedure capture from sessions) is mostly distinct, and the explicit boundary 'does not automatically extract or save memories' separates it from general memory skills, leaving only minor overlap risk with closely related skills.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: sickn33/agentic-awesome-skills
Path: skills/cc-skill-continuous-learning/SKILL.md
Commit: b1aebac

Reviewed: ~17 hours 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.