reflect

Use when the user asks to reflect on the CURRENT session, analyze the agent's own process, audit context usage in this conversation, or extract lessons from how the current task was executed. Do NOT trigger for historical multi-session analysis — use reflect-by-history for that. Do NOT trigger on plain "what did you do?" style recaps.

Quality

82%

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

Quality

Content

77%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 body is a highly actionable, well-sequenced reflective workflow with strong validation checkpoints and templates, but it is somewhat verbose due to duplicated taxonomies and inlines reference-grade material that has no bundle file to offload it to.

Suggestions

Deduplicate the error-type taxonomy: keep it in the Context block and reference it from step 6 instead of restating the full list, to recover token budget.

Extract the Behavioral/Technical/Discovery taxonomies and the worked example into a references/ file (e.g. REFLECTION_TAXONOMY.md) and link to it from SKILL.md, improving progressive disclosure.

Consolidate the FR-DOC-RESCUE constraint into one location and remove the non-English parenthetical ("Хотите, чтобы я создал…?") or replace it with an English equivalent for consistency.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but padded in places — error-type taxonomies are duplicated between the Context block and step 6, the FR-DOC-RESCUE rule is restated across rules/instructions/step 14, and an untranslated aside ("Хотите, чтобы я создал…?") adds noise.	3 / 5
Actionability	Fully executable guidance: literal report templates with substituted fields, a required literal token ("/flowai:plan"), a strict section schema for findings, and a complete worked example — copy-paste ready.	5 / 5
Workflow Clarity	A clear 14-step sequence with an explicit self-criticism validation checkpoint (step 13), feedback loops, and a cleanly separated read-only decision-rescue step (2b) with FORBIDDEN guardrails.	5 / 5
Progressive Disclosure	No bundle files exist and all content is inlined in SKILL.md; the large error/discovery taxonomies and worked example are candidates for separate reference files, leaving structure good but with inline material that should be split out.	3 / 5
	Total	16 / 20 Passed

Description

87%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 is well-structured with explicit trigger guidance, concrete actions, and clear negative boundaries that prevent mis-triggering against sibling skills. It strongly answers both what the skill does and when to use it.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — "reflect on the CURRENT session", "analyze the agent's own process", "audit context usage", "extract lessons" — with only minor coverage gaps, matching the anchor listing several specific actions.	4 / 5
Completeness	Explicitly answers both what (reflect/analyze/audit/extract lessons) and when ("Use when the user asks to reflect…") with concrete trigger phrases plus negative boundary guidance.	5 / 5
Trigger Term Quality	Good natural-phrase coverage ("reflect on", "audit context usage", "extract lessons") in correct third-person voice, with a few common synonyms missing and slight internal-jargon leaning.	4 / 5
Distinctiveness Conflict Risk	A clear niche with explicit negative triggers distinguishing it from reflect-by-history and plain recaps, minimizing conflict risk.	5 / 5
	Total	18 / 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: korchasa/flowai-plugins
Path: plugins/flowai/skills/reflect/SKILL.md
Commit: b4ba256

Reviewed: ~22 hours 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.