CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

session-status

Use when a session must record and report its own state — writes a Status block into its task file and opens the report with the state, the operator's part and what is left. Not for the project task list (tasks-overview) or goal check (check-goals).

Quality

86%

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

92%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 exemplary instruction-only skill: concrete commands, an exact output template, explicit decision logic, conditional commit handling, and a verification checklist. The only room for improvement is trimming minor duplication between the Overview and Context sections.

DimensionReasoningScore

Conciseness

The body is efficient and operational — rules are terse, commands are specific, and nothing explains concepts Claude already knows. Minor trimmable redundancy remains (the three-opening-lines idea appears in both Overview and Context), so it sits at 4 rather than 5's "every token earns its place".

4 / 5

Actionability

Fully executable for an instruction-only skill: exact commands (`git rev-parse --git-dir`, `git rev-parse --git-common-dir`, `git commit <task file> -m "docs(tasks): update session status"`, `date`), a copy-paste-ready six-bullet `## Status` template, exact three opening report lines, and explicit state-decision logic covering the common cases. Per the rubric's code-vs-instruction note, absence of code is not penalized when guidance is this concrete.

5 / 5

Workflow Clarity

A clear 5-step sequence with explicit validation checkpoints: reading the task file from disk ("Do not rely on memory"), the worktree-vs-shared-checkout check before any commit, an edge-case path when no task file exists, and a 5-item Verification checklist. The operation edits a single task file and is neither destructive nor batch, so the feedback-loop cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist, but none are needed: every section (Context, Rules, Instructions, Verification) is core operational content that belongs inline, and the tagged, well-labeled sections make navigation easy. Content is appropriately placed and nothing that should be externalized is inlined.

5 / 5

Total

19

/

20

Passed

Description

73%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 solid description with an explicit use-when clause, concrete actions, and excellent disambiguation against neighboring skills via negative triggers. Its main weaknesses are limited action coverage and a trigger clause that paraphrases the capability instead of listing natural user phrases.

Suggestions

List more of the skill's concrete actions in the description (e.g., recording follow-ups, reporting branch/commit/push state, the fixed three-line report) to raise specificity from naming 1-2 actions to several.

Add natural user-side trigger phrases such as "status update", "progress report", or "what is left" to the use-when clause so the trigger matches what a user would actually say.

Mention the four states (working, blocked on operator, done, failed) in the description to sharpen both what the skill does and when it applies.

DimensionReasoningScore

Specificity

The description names the domain and two concrete actions — "writes a Status block into its task file and opens the report with the state, the operator's part and what is left" — but coverage is not comprehensive (no mention of follow-ups, branch reporting, or verification). This matches anchor 3 ("1-2 concrete actions, but not comprehensive") rather than 4, which requires several specific actions; wording like "the operator's part" is also slightly abstract.

3 / 5

Completeness

Both "what" (writes a Status block, opens the report with three lines) and "when" (explicit "Use when a session must record and report its own state") are present. Falls short of 5 because the trigger clause restates the capability rather than naming concrete user-side trigger phrases.

4 / 5

Trigger Term Quality

Good natural keyword coverage: "session", "state", "Status", "report", "task file", "what is left" are phrases a user would plausibly say. Not 5 because common variations such as "progress update", "status update", or "blocked" are missing, leaving a few natural terms uncovered.

4 / 5

Distinctiveness Conflict Risk

A clear niche (session self-status reporting) with explicit negative triggers — "Not for the project task list (tasks-overview) or goal check (check-goals)" — that disambiguate it from sibling skills, giving minimal conflict risk.

5 / 5

Total

16

/

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

korchasa/flowai-plugins

Path

plugins/flowai-swarm/skills/session-status/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.