CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

retain-learning

Retain a new learning, discovery, or hard-won insight into Hindsight so it's available in future sessions.

Quality

81%

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

100%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 an exemplary short-form instructional skill: a lean five-step workflow, concrete classification taxonomy and memory schema, and a complete worked example that leaves nothing ambiguous. No bundle files are referenced or needed, and the structure is fully self-contained.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: a numbered step list, a compact category taxonomy, memory field definitions, and one fully worked example — no explanations of concepts Claude already knows and no padded sections. Every token earns its place, matching the anchor 'Lean and efficient; assumes Claude's intelligence'.

5 / 5

Actionability

As an instruction-only skill, it provides fully concrete guidance: five explicit steps, six named classification categories, five specified memory fields, the exact tool to call ('Store the memory using the Hindsight retain tool'), and a complete worked example (the TypeORM migration note) covering the common case. Nothing is left as vague direction.

5 / 5

Workflow Clarity

The sequence (parse, classify, structure, store, confirm) is clear and unambiguous, with step 5 acting as a confirmation checkpoint, and step 1 covers the empty-arguments edge case. This is a simple, non-destructive, non-batch single task, so the simple-skill exception applies and the clear sequence merits 5.

5 / 5

Progressive Disclosure

The skill is under 50 lines, is a single task with no need for external references (none exist in the bundle), and is organized into well-labeled sections ('Steps', 'Example') plus a $ARGUMENTS marker. Per the guideline for short single-purpose skills, this merits a 5.

5 / 5

Total

20

/

20

Passed

Description

53%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 concise, in third person, and clearly states what the skill does with a specific target system (Hindsight), but it lacks any explicit 'Use when...' trigger guidance and misses natural user phrasings like 'remember this' or 'save this'. These gaps cap completeness and trigger-term quality at the midpoint.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user says 'remember this', 'save this learning', or shares an insight worth keeping for future sessions." — this addresses completeness (currently capped at 3).

Include natural synonyms users would actually say — 'remember', 'save', 'note this', 'keep this in mind' — alongside 'retain', to improve trigger-term quality.

Briefly name one or two more concrete actions (e.g. 'classifies it into categories and structures it as a memory') to lift specificity beyond a single stated action.

DimensionReasoningScore

Specificity

The phrase 'Retain a new learning, discovery, or hard-won insight into Hindsight' names the domain and one concrete action, but does not enumerate the other specific actions the skill performs (classify, structure, confirm). It matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' — not the level-4 anchor, which requires several listed actions.

3 / 5

Completeness

The 'what' is clear (retain a learning into Hindsight for future sessions), but there is no 'Use when...' clause or equivalent explicit trigger guidance — only a purpose statement. Per the judging guidelines, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

It includes relevant keywords ('learning', 'discovery', 'hard-won insight', 'retain', 'Hindsight') but misses the natural phrases users would actually say, such as 'remember this', 'save this', or 'note this'. This matches 'Some relevant keywords but missing common variations or synonyms' rather than the level-4 'Good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

The named 'Hindsight' system and the specific framing 'retain a new learning... into Hindsight' give it a mostly distinct niche with only minor overlap risk against generic memory/journaling skills. It is more distinct than anchor 3 but lacks the fully distinct trigger phrasing of anchor 5.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

AndreJorgeLopes/devflow

Path

skills/retain-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.