CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

reflect-session

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

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

The canonical home for this skill is reflect-session in AndreJorgeLopes/devflow

SKILL.md
Quality
Evals
Security

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 lean, highly actionable workflow: concrete review prompts, a defined learning taxonomy, an exact output template, and pre/post-write checkpoints around memory retention. Its only weaknesses are minor redundancy in the opening line and the absence of error-recovery guidance for failed retention calls.

DimensionReasoningScore

Conciseness

The body is efficient with every section earning its place (enumerated review prompts, one-line category definitions, a compact output template), but the opening line "You are wrapping up a session. Reflect on what happened and consolidate the valuable learnings" re-states the description, and "with proper categorization" in step 5 is redundant after the step-2 taxonomy — minor instances of over-explanation that could be trimmed.

4 / 5

Actionability

For an instruction-only skill the guidance is fully executable: enumerated review questions in step 1, a six-category taxonomy with definitions, a copy-paste presentation template in step 3, an explicit default in step 4 ("Default is all of them unless the user removes some"), and a named tool invocation ("Hindsight `retain` tool") — specific and unambiguous throughout.

5 / 5

Workflow Clarity

The six steps are clearly numbered and sequenced with two explicit human checkpoints (user approval before retention in step 4, confirmation of count and titles in step 6), but there is no error-recovery guidance (e.g., what to do if a retain call fails or retention is partial), which keeps it at anchor 4 rather than 5's 'feedback loops for error recovery'.

4 / 5

Progressive Disclosure

The body is roughly 54 lines, entirely self-contained with no need for external references, and well-organized into clear sections ("## Steps", "## Important"), qualifying for a 5 under the under-50-line well-organized-sections exception.

5 / 5

Total

18

/

20

Passed

Description

53%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 communicates a clear 'what' anchored by the distinctive Hindsight system, but it entirely lacks 'when to use it' trigger guidance and misses natural synonyms like retrospective or wrap-up. It is serviceable but below the standard of the good examples, which pair capabilities with explicit trigger clauses.

Suggestions

Add an explicit trigger clause, e.g. "Use when wrapping up a session, when the user asks to reflect on the session, do a retrospective, or save lessons learned."

Include natural synonyms and phrasings users would actually say ("wrap up", "retrospective", "lessons learned", "debrief") to improve trigger-term coverage.

Replace the abstract lead verb "Reflect on the current session" with more concrete capability language (e.g., "Reviews the session, categorizes insights, and retains them in Hindsight").

DimensionReasoningScore

Specificity

The description names the domain and two concrete actions ("extract learnings", "consolidate them into Hindsight for future recall") but the lead verb "Reflect on the current session" is abstract and coverage is not comprehensive, matching anchor 3 rather than anchor 4's 'several specific actions'.

3 / 5

Completeness

It clearly answers 'what' ("Reflect on the current session, extract learnings, and consolidate them into Hindsight") but provides no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

It includes some relevant natural keywords ("Reflect", "session", "learnings", "recall") but misses common variations and synonyms users would say, such as "retrospective", "wrap up", "lessons learned", or "debrief", fitting anchor 3.

3 / 5

Distinctiveness Conflict Risk

Naming the specific "Hindsight" system gives the skill a clear niche and mostly distinct identity, but without explicit trigger phrases it carries minor overlap risk with generic memory-retention skills, fitting anchor 4 rather than anchor 5's 'distinct triggers'.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

devflow-plugin/skills/reflect-session/SKILL.md

Reviewed

Table of Contents

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.