CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

session-lifecycle

Use at the START of every working session, at the END of every working session, and immediately after any context compaction/summarization. Defines the orientation protocol (first steps), the handoff protocol (last steps), and how to exploit the fact that agent sessions start from a clean state.

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

An exceptionally actionable, well-sequenced protocol skill: concrete commands, explicit validation checkpoints, and genuine error-recovery loops in both the orientation and handoff workflows. The only deductions are minor rhetorical padding and a single-file structure that could offload detail to reference files.

DimensionReasoningScore

Conciseness

The body is dense and imperative and assumes Claude's competence ("never trust a summary's paraphrase of it", "A timeout is not a failure signal"), with only minor rhetorical flourishes like "A past session that did work without updating these stole from you" that could be trimmed. It is not 5 because a few motivational asides don't strictly earn their tokens, and not 3 because the padding is minor and mostly load-bearing rationale.

4 / 5

Actionability

Guidance is copy-paste concrete throughout: "git status + git log --oneline -10", "./scripts/trace-audit.bb", "rg 'REQ-<ID>'", "br ready --json", and the scoped commit format "<scope>: <description>" with REQ ID in the body. Per the rubric's scoring note, this instruction-only skill is fully actionable without code examples.

5 / 5

Workflow Clarity

Both the orientation protocol (steps 1–8) and handoff protocol (steps 1–5) are clearly sequenced with explicit validation checkpoints ("Run the baseline green", "Never end mid-red", run gates before ending) and error-recovery feedback loops (dirty tree → stop and report; timeout → extend the clock, don't relaunch). This matches the top anchor including checklists and recovery loops.

5 / 5

Progressive Disclosure

The single file is well-organized with clear sections (First steps, Environment hazards, After compaction, Last steps, Work loop, Exploiting the clean state) and no nested references, but at ~150 lines with no bundle files, content like the work-loop and tracker-discipline details could be split into a one-level-deep reference. Good structure with minor organization gaps fits anchor 4.

4 / 5

Total

18

/

20

Passed

Description

83%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 both what the skill defines and exactly when to use it, with concrete session-boundary and compaction triggers. Trigger coverage is good though a few natural synonyms (handoff, new session) are absent, and the named capabilities are protocol-level rather than fully granular.

DimensionReasoningScore

Specificity

Names three concrete deliverables — "the orientation protocol (first steps), the handoff protocol (last steps), and how to exploit the fact that agent sessions start from a clean state" — which matches the several-specific-actions level. It falls short of 5 because these are protocol categories rather than granular concrete actions.

4 / 5

Completeness

Explicitly answers both questions: "Use at the START of every working session, at the END of every working session, and immediately after any context compaction/summarization" (when) and "Defines the orientation protocol... the handoff protocol... how to exploit..." (what), with concrete trigger phrases — a clear match for the top anchor.

5 / 5

Trigger Term Quality

Natural trigger phrases like "START of every working session", "END of every working session", and the synonym pair "context compaction/summarization" give good keyword coverage. A few natural terms (e.g., "handoff", "new session") are missing, keeping it below 5.

4 / 5

Distinctiveness Conflict Risk

The session-lifecycle niche (orientation/handoff protocols around agent amnesia) is mostly distinct with session-boundary triggers. Minor overlap risk remains with closely related memory/handoff skills, so it does not reach the clear-niche top anchor.

4 / 5

Total

17

/

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

igouss/gitweb-rs

Path

.claude/skills/session-lifecycle/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.