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

74%

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

78%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 lean, well-structured instruction skill with a genuinely actionable procedure, strong privacy/authorization guardrails, and honest limitations. Its main weakness is reference integrity: both file references in the body point at files that are missing or mismatched in the bundle.

Suggestions

Ship evaluate-session.sh and a skill-level config.json containing min_session_length in the bundle so both inline references resolve, and make the bash command path consistent with the [evaluate-session.sh](evaluate-session.sh) link.

Rename or repath the config reference (e.g., [helper config](config/helper.json)) so it cannot collide with an unrelated config.json at the skill root.

Show the helper's expected stderr output for the threshold-reminder case so users can verify correct invocation without reading the script.

Dimension	Reasoning	Score
Conciseness	Dense, imperative prose with no padding and no explanation of concepts Claude already knows ("The helper counts JSONL objects whose top-level `type` equals `user`. It prints a count and review reminder to stderr"); every line adds guidance the model does not already have, matching the lean/efficient anchor.	5 / 5
Actionability	Concrete instruction-only guidance: a 7-step procedure with specific directives ("Include an expected result and a counterexample", "Remove secrets, user names, absolute personal paths"), an executable helper command, and a worked example. Minor gaps remain, such as the helper's exact output format not being shown, so it is not fully copy-paste ready.	4 / 5
Workflow Clarity	A clear 7-step sequence with explicit checkpoints (step 2 verifies the fix was actually exercised; step 7 says to "read back the saved result"), but there is no error-recovery feedback loop (validate -> fix -> retry), which the anchor-5 example requires.	4 / 5
Progressive Disclosure	Sections are well organized and references are clearly signaled and one level deep, but the referenced bundle files do not exist: evaluate-session.sh is absent from the bundle, the [config.json](config.json) link collides with the evaluation config rather than a skill config containing min_session_length, and the bash command uses a different path (skills/cc-skill-continuous-learning/evaluate-session.sh) than the inline link.	3 / 5
	Total	16 / 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.

A concise, third-person description that clearly states what the skill does and when to use it, with a useful negative-scope clause. It is slightly thin on concrete trigger phrases and lists only one main action, keeping it just short of top marks.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ("Turn a completed debugging session or repeated user correction into a small, evidence-backed procedure") but does not list several specific actions, matching the 1-2-concrete-actions anchor rather than the multi-action anchor above.	3 / 5
Completeness	Clearly answers what ("Turn a completed debugging session... into a small, evidence-backed procedure") and has an explicit when-clause ("Use for explicit requests to capture reusable lessons"), but the trigger situations could be more concrete (e.g., after a resolved failure), fitting anchor 4 rather than 5.	4 / 5
Trigger Term Quality	Includes several natural trigger phrases ("debugging session", "repeated user correction", "capture reusable lessons") with good coverage, though common user variations like "remember this", "lessons learned", or "postmortem" are missing, so it does not reach comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche and the clause "does not automatically extract or save memories" explicitly disambiguates it from memory-management skills, leaving only minor overlap risk with those closely related skills.	4 / 5
	Total	15 / 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: 7b534bc

Reviewed: 5 days 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.