recall-before-task

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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Content

100%

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 tight, actionable, well-sequenced instruction skill that assumes Claude's competence, provides concrete recall guidance and an output template, and includes explicit safeguards against fabricated or missing memories.

Dimension	Reasoning	Score
Conciseness	The body is lean and instructional, with no padding explaining what memory or Hindsight is; every section (Steps, synthesis categories, output template, Important) earns its place.	3 / 3
Actionability	Gives concrete, specific guidance: use the Hindsight 'recall' tool with multiple recall calls keyed to files/modules and named domain concepts ('authentication', 'worktrees', 'CI pipeline'), plus a copy-ready output template.	3 / 3
Workflow Clarity	Five clearly sequenced steps with an explicit 'Important' checklist and validation-style safeguards ('If no memories are retrieved, say so explicitly', 'Do not fabricate memories') appropriate for this single-task skill.	3 / 3
Progressive Disclosure	A simple skill under 50 lines with no bundle files; content is well-organized into Steps and Important sections, which satisfies progressive disclosure for a skill needing no external references.	3 / 3
	Total	12 / 12 Passed

Description

60%

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 states concrete capabilities and has a fairly distinct niche tied to pre-task memory recall, but it lacks an explicit 'Use when...' trigger clause and leans on a tool name that may not match user phrasing, capping completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when starting a new task or when past context might prevent repeating earlier mistakes.'

Include more natural trigger phrasings a user would say beyond the 'Hindsight' brand name, such as 'past decisions', 'lessons learned', or 'project memory'.

Tighten the what/when pairing so the trigger condition is stated explicitly rather than implied by 'before starting a task'.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Recall relevant memories', 'Injects past learnings, decisions, and context' — rather than vague language.	3 / 3
Completeness	Answers 'what' (recall memories, inject past learnings/decisions/context) but the 'when' is only implied; there is no explicit 'Use when...' clause, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Includes some natural terms ('recall memories', 'context', 'before starting a task') but leans on the proprietary 'Hindsight' name a user may not naturally say, and is missing common variations.	2 / 3
Distinctiveness Conflict Risk	The 'before starting a task' + 'recall memories from Hindsight' framing is a reasonable niche, but the recall/context concept could still overlap with other context-gathering skills.	2 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: AndreJorgeLopes/devflow
Commit: 9556c94

Reviewed: 2 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.