recall-before-task

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

Quality

63%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/recall-before-task/SKILL.md

Quality

Content

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a reasonably well-structured skill for recalling context from Hindsight before starting a task. Its strengths are clear workflow sequencing, a concrete output template, and good edge-case handling (no memories found, don't fabricate). Its main weaknesses are slightly verbose explanations and lack of specific tool invocation syntax, which reduces actionability.

Suggestions

Specify the exact Hindsight tool invocation syntax (tool name, parameter names, example call) rather than just referencing 'the Hindsight recall tool' generically.

Trim explanatory rationale (e.g., 'Past context prevents repeated mistakes') that Claude doesn't need—just state the rule directly.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but includes some unnecessary explanation. The 'Important' section's first bullet ('even if the task seems simple. Past context prevents repeated mistakes.') explains rationale Claude doesn't need. The step descriptions could be tighter—e.g., step 1 'Parse the task description' is somewhat obvious. However, it's not egregiously verbose.	2 / 3
Actionability	Provides a clear process with specific recall strategies (full task description, file paths, domain concepts) and a concrete output format template. However, it references 'Hindsight tools' and a 'recall' tool without specifying exact tool names, parameters, or invocation syntax. The guidance is structured but not fully executable/copy-paste ready.	2 / 3
Workflow Clarity	The 5-step sequence is clearly ordered with explicit instructions at each stage. It includes a validation-like checkpoint (step 5: ask user before proceeding), handles the empty-result case ('No prior memories found'), and has a clear output format. For a non-destructive recall operation, this level of workflow clarity is appropriate and complete.	3 / 3
Progressive Disclosure	For a simple, single-purpose skill under 50 lines with no need for external references, the content is well-organized with clear sections (Steps, Important, output format template). No bundle files are needed and none are referenced, which is appropriate.	3 / 3
	Total	10 / 12 Passed

Description

57%

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 identifies a clear niche (memory recall from Hindsight) and is distinctive, but lacks explicit trigger guidance ('Use when...') and natural user-facing keywords. The actions described are somewhat abstract ('injects past learnings, decisions, and context') rather than listing concrete specific operations.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when starting a new task, resuming work, or when the user asks to recall previous decisions or context.'

Include more natural trigger terms users might say, such as 'remember', 'previous session', 'what did we decide', 'past context', or 'prior work'.

Dimension	Reasoning	Score
Specificity	Names the domain (memory recall from Hindsight) and some actions (injects past learnings, decisions, context), but doesn't list multiple concrete specific actions beyond the general concept of recalling and injecting memories.	2 / 3
Completeness	The 'what' is reasonably clear (recall memories from Hindsight and inject them into the session), but there is no explicit 'Use when...' clause. The phrase 'before starting a task' partially implies when, but it's not an explicit trigger guidance.	2 / 3
Trigger Term Quality	Includes some relevant terms like 'memories', 'Hindsight', 'past learnings', 'decisions', and 'context', but lacks natural user-facing trigger terms. Users are unlikely to say 'inject past learnings' — they might say 'remember', 'what did we decide', 'previous session', or 'recall context'.	2 / 3
Distinctiveness Conflict Risk	The mention of 'Hindsight' as a specific tool/system and the specific niche of recalling past memories/learnings makes this clearly distinguishable from other skills. It's unlikely to conflict with other skills.	3 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: AndreJorgeLopes/devflow
Commit: 8d872bf

Reviewed: 1 day 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.