CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

record-session

Records completed work progress to .trellis/workspace/ journal files after human testing and commit. Captures session summaries, commit hashes, and updates developer index files for future session context. Use when a coding session is complete, after the human has committed code, or to persist session knowledge for future AI sessions.

Quality

87%

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

80%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 highly actionable and well-structured: every instruction is an executable command, duplication is minimal, and the single-file layout fits the skill's scope. The main weakness is the absence of validation or verification steps around scripts that auto-commit batch changes to .trellis metadata.

Suggestions

Add a verification checkpoint after Step 2, e.g. re-run get_context.py or `git log -1` to confirm the journal entry and auto-commit landed, with guidance on what to do if add_session.py fails or partially writes.

Apply the same validation discipline to archiving: before `task.py archive <task-name>`, instruct the reader to confirm the task's acceptance criteria via the context output, since archiving auto-commits and moves task files.

Trim the Script Command Reference table so it only lists commands not already shown in the steps (e.g. keep `task.py list`), or drop the duplicated flag strings to reduce redundancy.

DimensionReasoningScore

Conciseness

The body is lean and operational ("Do NOT run `git commit` directly", "judge by work status, not the `status` field") with no explanation of known concepts. Not 5: the Script Command Reference table repeats the exact `get_context.py`, `add_session.py`, and `task.py archive` commands already shown in the steps, which is trimmable duplication.

4 / 5

Actionability

Every step is a copy-paste-ready command with real flags: both the simple form (`--title "Session Title" --commit "hash1,hash2" --summary "..."`) and the heredoc `--stdin` variant, plus `task.py archive <task-name>`. Not 4: the examples are fully executable and cover the common cases with no gaps.

5 / 5

Workflow Clarity

The two-step sequence is clear with a prerequisite gate ("only be used AFTER the human has tested and committed") and archive decision criteria, but the scripts "Auto-commits .trellis/workspace and .trellis/tasks changes" — batch git operations — with no post-run verification or error-recovery step, capping the score at 3 per the batch-operation guideline. Not 4: validation is entirely absent, not merely gappy.

3 / 5

Progressive Disclosure

This is a simple single-file skill (~60 lines) with well-organized sections ("Record Work Progress", "Script Command Reference") and no content that belongs in a separate file; no bundle files exist and no references are nested. The simple-skill exception applies — clear structure alone warrants 5.

5 / 5

Total

17

/

20

Passed

Description

88%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: third-person voice, concrete actions tied to specific paths, and an explicit multi-condition "Use when..." clause. Trigger coverage is good but lacks common synonyms, and generic session-completion triggers leave minor conflict risk with other session-management skills.

DimensionReasoningScore

Specificity

"Records completed work progress to .trellis/workspace/ journal files", "Captures session summaries, commit hashes", and "updates developer index files" are multiple concrete actions with specific paths that comprehensively cover the skill's behavior. Not 4: there are no gaps in coverage — every action the skill performs is named.

5 / 5

Completeness

Explicitly answers "what" ("Records completed work progress... Captures session summaries, commit hashes, and updates developer index files") and "when" ("Use when a coding session is complete, after the human has committed code, or to persist session knowledge for future AI sessions") with concrete trigger phrases. Not 4: the "when" clause is explicit and specific rather than merely present.

5 / 5

Trigger Term Quality

Triggers like "coding session is complete", "after the human has committed code", and "persist session knowledge" are natural phrases users would say. Not 5: common variations and synonyms such as "session recap", "log what was done", or "journal" are missing.

4 / 5

Distinctiveness Conflict Risk

The ".trellis/workspace/ journal files" niche and "after the human has committed code" clearly separate it from commit-message and git-helper skills. Not 5: broad triggers like "session is complete" carry minor overlap risk with other session-management or context-persistence skills.

4 / 5

Total

18

/

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

202780181/lingxiData

Path

.agents/skills/record-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.