CtrlK
BlogDocsLog inGet started
Tessl Logo

reflect-session

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

60

Quality

68%

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

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.

The content is a lean, well-structured, actionable workflow with an explicit user-approval gate before retaining memories. Its main gap is the absence of a concrete retained-learning example and retain-tool invocation format.

Suggestions

Add one concrete example of a retained learning and the exact Hindsight `retain` tool call so the action is copy-paste ready.

Specify a small error-recovery step if a `retain` call fails (retry, surface the failure, continue with remaining items).

Drop or clarify the "Duration" template field since session length is often hard for Claude to estimate.

DimensionReasoningScore

Conciseness

The body is efficient, uses bullet lists and a template, and assumes Claude's competence without explaining known concepts; only minor items (e.g. the "Duration" placeholder) could be trimmed, fitting "efficient; minor instances of over-explanation."

4 / 5

Actionability

Provides concrete sequenced steps, a presentation template, explicit learning categories, and names the Hindsight `retain` tool, but lacks a concrete example of a retained memory or the retain call format, leaving minor gaps.

4 / 5

Workflow Clarity

A clear six-step sequence includes a user-approval checkpoint (present, ask which to retain, then retain) before the batch write, but there is no explicit error-recovery loop if a retain call fails.

4 / 5

Progressive Disclosure

The skill is a short, self-contained overview with well-organized sections (Steps, Important) and no need for external references, matching the under-50-lines exception for progressive disclosure.

5 / 5

Total

17

/

20

Passed

Description

58%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 clearly conveys the skill's purpose and concrete actions but lacks an explicit "when to use" trigger clause, which caps its completeness and trigger-term scores. It is distinct within its niche yet could be sharpened with natural trigger phrasing.

Suggestions

Add an explicit "Use when..." clause naming natural triggers, e.g. "Use when wrapping up a session, the user asks to reflect, or wants to save learnings to Hindsight."

Broaden trigger-term coverage with user-facing synonyms like "retrospective", "lessons learned", or "session recap".

Tighten the what/when pairing so both halves are explicitly answered in one sentence.

DimensionReasoningScore

Specificity

Names the domain (session reflection) and three concrete actions — "Reflect on", "extract learnings", "consolidate them into Hindsight" — placing it at "several specific actions" but not comprehensive coverage.

4 / 5

Completeness

Clearly states what the skill does but omits any explicit when-to-use guidance; per the rubric a missing "Use when..." clause caps completeness at 3.

3 / 5

Trigger Term Quality

Includes some natural terms a user might say ("reflect", "learnings", "Hindsight") but offers no explicit "Use when..." trigger clause and misses common synonyms, matching "some relevant keywords but missing common variations."

3 / 5

Distinctiveness Conflict Risk

The "Hindsight" consolidation niche and "session reflection" framing make it mostly distinct with only minor overlap risk against generic memory/learning skills, though no explicit triggers narrow it further.

4 / 5

Total

14

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
AndreJorgeLopes/devflow
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.