CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cc-skill-continuous-learning

Development skill from everything-claude-code

1.54x
Quality

32%

Does it follow best practices?

Impact

99%

1.54x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/cc-skill-continuous-learning/SKILL.md

The canonical home for this skill is cc-skill-continuous-learning in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

30%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 a placeholder: a heading, a typo'd fragment ("Development skill skill."), and a 'When to Use' section that circularly points to an overview of workflows/actions that was never written. While commendably brief, it provides no actionable guidance of any kind.

Suggestions

Write an actual overview section defining the skill's workflow, then replace the circular sentence "This skill is applicable to execute the workflow or actions described in the overview" with a numbered step sequence for the continuous-learning process.

Fix the duplicated-word fragment "Development skill skill." and replace it with a one-sentence statement of what the skill concretely does.

Add validation/checkpoint steps (e.g., verify captured feedback is accurate before persisting it to a skill file) if the workflow involves batch updates to SKILL.md files, since missing feedback loops cap workflow quality.

DimensionReasoningScore

Conciseness

The body is only ~4 lines with zero padding or explanation of concepts Claude already knows, so it is broadly efficient. Not 5 because "every token earns its place" fails: the duplicated word in "Development skill skill." and the circular phrase "described in the overview" (no overview exists) are wasted tokens.

4 / 5

Actionability

There is no concrete code, command, or instruction anywhere; the sole 'When to Use' sentence defers to "the workflow or actions described in the overview", which does not exist. This matches 'Entirely vague or abstract; no concrete code or commands; only describes rather than instructs' — it barely even describes.

1 / 5

Workflow Clarity

No steps or sequence are present, and the referenced workflow is never defined, matching 'Steps missing or incoherent; no sequence; no validation for risky operations'. A 2 would require at least a rough step sequence, which the body does not contain.

1 / 5

Progressive Disclosure

The body is short, has a section heading, and inlines nothing that belongs elsewhere, but the 'described in the overview' phrase is a broken navigation signal pointing at nonexistent content. This fits 'Some structure but could be better organized; references present but not clearly signaled' better than 5 ('well-organized sections' with clear content) and better than 2 (which requires inlined or buried bulk content).

3 / 5

Total

9

/

20

Passed

Description

3%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 effectively metadata, not a description: it states the skill's origin ("from everything-claude-code") and a vague category ("Development skill") without any capability, trigger context, or distinguishing information. A user or Claude would have no basis to know what the skill does or when to invoke it.

Suggestions

Replace "Development skill from everything-claude-code" with a concrete inventory of what the skill actually does, e.g. "Continuously improves installed Claude Code skills by capturing feedback and updating SKILL.md files" — name 3-4 specific actions in third person.

Append an explicit 'Use when...' clause with natural trigger phrases and synonyms, e.g. "Use when the user asks to update, refine, or learn from past skill usage, or mentions skill self-improvement or feedback capture."

Add distinguishing trigger terms (skill feedback, skill refinement, continuous learning, SKILL.md updates) so the skill does not collide with every general development-related skill in the library.

DimensionReasoningScore

Specificity

"Development skill from everything-claude-code" contains no concrete actions at all — "Development skill" is pure abstraction and the rest is provenance metadata. This matches the anchor 'Entirely vague; no concrete actions; pure abstract language' exactly; it cannot be 2 because even a generic action verb like 'Processes PDF files' is absent.

1 / 5

Completeness

The 'what' is extremely vague ("Development skill") and the 'when' is entirely missing, matching 'Missing both what and when, or both are extremely vague'. A 3 would require a clear 'what', which is not present; the missing 'Use when...' clause already caps this dimension at 3 regardless.

1 / 5

Trigger Term Quality

There are no natural keywords a user would say when needing this skill; "development" is entirely generic and "everything-claude-code" is a repository name, not a trigger phrase. It clearly matches the anchor 'No natural keywords; only technical jargon or entirely generic language' rather than 2, which requires at least a generic but domain-anchored keyword like 'files'.

1 / 5

Distinctiveness Conflict Risk

"Development skill" is one very broad domain that would overlap with many (perhaps most) development-related skills, matching 'Very broad; high overlap risk with many similar skills'. Not 1 because it does not span multiple unrelated domains like 'code and documents'; the repo name adds a sliver of distinctiveness but functions as provenance, not a trigger.

2 / 5

Total

5

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/cc-skill-continuous-learning/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.