CtrlK
BlogDocsLog inGet started
Tessl Logo

recall-before-task

Recall relevant memories from Hindsight before starting a task. Injects past learnings, decisions, and context into the current session.

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/recall-before-task/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 tight, well-structured instruction-only skill with a clear multi-step workflow and good organization. The main gap is actionability could be nudged toward copy-paste-ready examples (e.g. sample recall tool invocations) and workflow clarity toward explicit validation checkpoints.

DimensionReasoningScore

Conciseness

The body is lean, assumes Claude's competence, contains no concept padding, and every section (Steps, Important, the template, $ARGUMENTS) earns its place — matches the 5 anchor.

5 / 5

Actionability

Gives concrete actionable guidance (specific recall calls for full query, file paths, and domain concepts; a four-category synthesis; a presentation template) but as an instruction-only skill it stops short of copy-paste-ready commands, matching the 4 anchor.

4 / 5

Workflow Clarity

A clear 5-step sequence with an interaction checkpoint at step 5 ('Ask the user') and explicit no-memory handling, but validation checkpoints are light rather than explicit feedback loops — fits the 4 anchor; the destructive/batch cap does not apply to this non-destructive skill.

4 / 5

Progressive Disclosure

Under 50 lines, single-purpose, well-organized into ## Steps and ## Important with no need for external bundle files — the rubric's simple-skill exception lets this score 5.

5 / 5

Total

18

/

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 clearly states what the skill does but omits any explicit 'when to use it' trigger guidance, which caps completeness. Trigger term coverage is moderate and would benefit from natural user phrasing and synonyms.

Suggestions

Add an explicit 'Use when...' clause stating when to invoke this skill (e.g. before starting any new task) to raise completeness.

Include natural user-facing trigger terms and synonyms beyond 'Hindsight' and 'memories' (e.g. 'past context', 'recall decisions', 'learnings').

List a few more concrete actions to round out specificity (e.g. 'recall by file path', 'recall by concept', 'synthesize into hard rules / gotchas').

DimensionReasoningScore

Specificity

Names the domain (memory recall from Hindsight) and a couple concrete actions ('Recall relevant memories', 'Injects past learnings, decisions, and context') but the action set is not comprehensive — closer to the 3 anchor than 4.

3 / 5

Completeness

Has a clear 'what' but no 'when'/'Use when' trigger guidance; per the rubric a missing 'Use when' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Contains relevant keywords ('Hindsight', 'memories', 'task') but lacks natural user-side phrasing and synonyms a user would actually say, fitting the 3 anchor 'some relevant keywords but missing common variations'.

3 / 5

Distinctiveness Conflict Risk

Tied to the specific 'Hindsight' tool with a distinct trigger (recall before a task), giving a clear niche with only minor overlap risk — matches the 4 anchor.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
AndreJorgeLopes/devflow
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.