reflect

Post-session reflection skill. Reads recent git history, artifacts, and context files to extract learnings and produce improvement proposals for skills, CLAUDE.md, hooks, and plan templates. Use after any substantive session.

Quality

75%

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 ./tiles/crafter/skills/reflect/SKILL.md

Quality

Content

78%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 well-structured, actionable skill body with a clear sequenced workflow, concrete tool usage, and excellent progressive disclosure that externalizes templates while keeping the core process inline. The only meaningful gaps are minor conciseness padding and the absence of an explicit edit-retry feedback loop in the apply step.

Suggestions

Add a short feedback loop to step 7 (Apply Approved Improvements) for the case where an Edit fails or a target file is missing — e.g., re-read, fix, and re-attempt before committing.

Consolidate the repeated 'BEFORE Plan Mode'/'IN Plan Mode' annotations (steps 1-3 share the BEFORE marker) into a single phase note to reduce redundant heading text.

Dimension	Reasoning	Score
Conciseness	The body is dense and purposeful and assumes Claude's competence (no exposition of git/CLAUDE.md/hooks), but the repeated BEFORE/IN Plan Mode heading annotations and the Git Unavailable Fallback section are minor trimmable padding.	4 / 5
Actionability	Concrete commands and tool calls are given throughout (git log/git diff invocations, TaskOutput block flags, commit message format, P1-P3 priority scheme), though the actual agent-prompt and artifact templates are externalized rather than inline.	4 / 5
Workflow Clarity	An explicit 8-step numbered sequence with phase markers, a user-review gate (step 6), per-commit atomicity, and post-apply verification ('git log --oneline -5'); the apply step lacks an explicit edit-fail/retry feedback loop, leaving a minor validation gap.	4 / 5
Progressive Disclosure	The body is a clean overview that signals one-level-deep references to references/agent-prompts.md, references/template.md, and references/improvement-guide.md (all of which exist), with verbose material externalized and the workflow/taxonomy kept inline.	5 / 5
	Total	17 / 20 Passed

Description

72%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.

A strong description that clearly states what the skill does across multiple concrete targets and gives an explicit when-clause. Its main weakness is thin natural-language trigger coverage within the description text itself, since the richer trigger phrases are kept in the separate triggers list.

Suggestions

Fold one or two natural trigger phrases (e.g., 'retrospective', 'what did we learn') into the description sentence so the keyword coverage does not depend solely on the triggers list.

Tighten the when-clause by naming the triggering situations inline (e.g., 'Use after finishing a feature, refactor, or debugging session where friction or learnings occurred') rather than the generic 'substantive session'.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions with named targets — 'Reads recent git history, artifacts, and context files to extract learnings and produce improvement proposals for skills, CLAUDE.md, hooks, and plan templates' — giving comprehensive coverage.	5 / 5
Completeness	Both 'what' (the read/extract/propose pipeline) and 'when' ('Use after any substantive session') are present, but the when-clause is a single generic statement rather than concrete trigger phrases.	4 / 5
Trigger Term Quality	The description surfaces only 'reflection' and 'session' as natural terms; richer natural phrases ('retrospective', 'what did we learn') live in the triggers list rather than the description text, leaving common variations missing.	3 / 5
Distinctiveness Conflict Risk	The post-session-reflection niche with its enumerated targets is mostly distinct, though 'reflection'/'substantive session' phrasing carries minor overlap risk with general review or introspection skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: ericjohnolson/tessl-test
Path: tiles/crafter/skills/reflect/SKILL.md
Commit: 2a98cc1

Reviewed: 4 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.