reflect-session

Reflect on the current session, extract learnings, and consolidate them into Hindsight for future recall.

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/reflect-session/SKILL.md

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.

The content is a well-structured, concise session-reflection workflow with concrete steps, a useful categorization taxonomy, and an output template; it is lean and easy to follow. The only gaps are a missing explicit feedback/validation loop after retention and unspecified retain-tool arguments.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: a tight categorization taxonomy, a compact template, and short bullet guidance with no padding or explanation of concepts Claude already knows, matching the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	It provides concrete numbered steps, an explicit output template, a named tool ('retain'), and a classification taxonomy, giving mostly executable guidance; it stops short of fully copy-paste-ready specification (the retain tool's exact arguments are not given), so it does not reach 5.	4 / 5
Workflow Clarity	The six steps are clearly sequenced with an explicit user-review checkpoint in step 4 ('Ask the user') and a confirm step; this is not a destructive/batch operation so the destructive cap does not apply, but there is no explicit validate-then-fix feedback loop after retention, leaving a minor validation gap.	4 / 5
Progressive Disclosure	No bundle files are present and the skill is single-purpose with well-organized sections (## Steps, ## Important), which per the scoring notes lets a simple skill score 5 on progressive disclosure with just clear organization.	5 / 5
	Total	18 / 20 Passed

Description

42%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 states a clear purpose and three actions but lacks any explicit 'Use when...' trigger guidance and uses no natural user-facing keywords, leaving its completeness and trigger quality below the good examples. It is reasonably distinct but would benefit from concrete trigger phrases.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when wrapping up a session, running a retrospective, or the user asks to capture learnings'.

Replace generic phrasing with concrete user-facing terms (e.g. 'session retrospective', 'post-mortem', 'capture lessons learned') to improve trigger-term coverage.

Specify the concrete deliverable in the description (e.g. 'categorize learnings and store them as Hindsight memories via the retain tool') to lift specificity from 3 toward 4.

Dimension	Reasoning	Score
Specificity	The description names the domain ('the current session') and three actions ('Reflect', 'extract learnings', 'consolidate them into Hindsight'), matching the anchor listing 1-2 concrete actions; the actions are somewhat abstract rather than fully concrete, so it does not rise to a 4.	3 / 5
Completeness	It gives a clear 'what' but no explicit 'when'/'Use when...' clause; per the judging guidelines a missing trigger clause caps completeness at 3, and the 'when' is only weakly implied elsewhere in the body.	3 / 5
Trigger Term Quality	It contains no natural phrases a user would say ('wrap up', 'retrospective', 'post-mortem'); 'Hindsight' is a tool name and the rest is generic phrasing, fitting the anchor with one or two generic keywords missing the natural terms users say.	2 / 5
Distinctiveness Conflict Risk	The session-reflection-plus-Hindsight niche is somewhat specific but the abstract phrasing around 'extract learnings' could overlap with general memory/recall skills, matching the 'somewhat specific but could still overlap' anchor rather than the more distinct 4.	3 / 5
	Total	11 / 20 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
Path: skills/reflect-session/SKILL.md
Commit: bd4b70c

Reviewed: 12 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.