CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

working-in-turns

Keep each turn bounded, checkpointed, and reviewable.

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./fleet-skills/working-in-turns/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 delivers unusually concrete operational guidance — exact timeouts, commands, sentinel formats, and a ready-to-use template — and handles destructive checkout operations with explicit validation. Its weaknesses are structural: the lifecycle is scattered across parallel bullets rather than sequenced, and the checkout-strategy and verdict-format instructions are restated multiple times, spending tokens on repetition.

Suggestions

Reorder the bullets (or add a short numbered lifecycle: turn start → before ending → PR handoff → review → verdict → checkout cleanup) so the sequence and its checkpoints are explicit rather than inferred.

State the checkout strategy once and reference it from the gate ask template instead of repeating it in the bullets, the template, and the closing line.

Add a brief in-line gloss or hyperlink context for internal jargon like "the row" and "the press", or replace those terms with self-describing ones.

DimensionReasoningScore

Conciseness

The body is mostly dense, high-value specifics (exact env var `COMMONLY_AGENT_RUN_TIMEOUT_MS`, value `2700000`, the SIGTERM consequence, exact `GATE: PASS`/`GATE: HOLD` sentinels), but the checkout-strategy guidance is repeated roughly four times (two bullets, inside the gate ask template, and a closing line) and the rules-44/51 verdict format is specified twice. Anchor 3 ("mostly efficient but... could be tightened") fits; anchor 4 is blocked by that repeated material.

3 / 5

Actionability

Guidance is largely executable: specific timeout values and timing targets, `gh pr ready` behavior, the exact sentinel format with first-line/final-line placement rules, and a copy-paste-ready gate ask template. It falls short of anchor 5 only due to minor gaps — unexplained jargon ("the row", "the press") and no concrete commands for "commit and push what you have".

4 / 5

Workflow Clarity

An implicit lifecycle exists (end turn early → open ready PR → one self-review round → answer CodeRabbit/get CI green → file verdict → checkout cleanup), and validation for the destructive checkout operations is explicitly present ("inspect... after checking for uncommitted work"; "Never use `git worktree remove --force` before checking"), so the destructive-operation cap does not apply. However, the steps are parallel bullets rather than a sequenced workflow, and checkpoints like CI-green are stated as rules rather than ordered gates — anchor 3 ("Steps listed but... checkpoints missing or implicit").

3 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files, the gate ask template is split into its own clearly-purposed section, and the external review-checklist references (rules 44 and 51) are well signaled and one level deep. It misses anchor 5 because the main bullet list interleaves turn management, PR etiquette, review rounds, and checkout hygiene without grouping or sub-headers — minor organization gaps per anchor 4.

4 / 5

Total

14

/

20

Passed

Description

17%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 is concise but far too abstract: it conveys a vague quality goal with no concrete actions, no natural trigger terms, and no guidance on when to use the skill. A reader cannot distinguish this skill from generic agent-workflow guidance, and it would rarely be surfaced when actually needed.

Suggestions

Add a 'Use when...' clause naming the concrete invocation contexts, e.g. 'Use when running multi-turn agent loops, when a turn is about to hit its run limit, or when handing off work via a pushed branch'.

List the concrete actions the skill prescribes — e.g. 'End turns before the run limit, commit and push an open PR, run one self-review round, file GATE: PASS/HOLD verdicts' — instead of abstract qualities like 'bounded, checkpointed, reviewable'.

Include natural trigger terms users and models would actually say or see ('run limit', 'timeout', 'SIGTERM', 'turn budget', 'PR gate') to improve both trigger matching and distinctiveness from generic workflow skills.

DimensionReasoningScore

Specificity

"Keep each turn bounded, checkpointed, and reviewable" names the agent-turn-management domain but the only actions are abstract qualities ("bounded", "checkpointed", "reviewable") — no concrete operations like committing, pushing, or filing verdicts. It is above anchor 1 (pure filler like "Helps with documents") but does not reach anchor 3, which requires 1-2 concrete named actions.

2 / 5

Completeness

The 'what' is vague ("keep each turn bounded...") and the 'when' is entirely missing — there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness. This is anchor 2 ("Has a vague 'what' and no 'when'") rather than 3, because even the 'what' lacks concrete detail.

2 / 5

Trigger Term Quality

The only keywords are internal jargon ("bounded", "checkpointed", "reviewable") that a user would never naturally say when they need this skill; natural phrases like "run limit", "timeout", "turn ended early", or "PR checkpoint" are absent. This matches anchor 1: only technical jargon or entirely generic language.

1 / 5

Distinctiveness Conflict Risk

The phrasing is very broad and would overlap with virtually any agent-workflow, loop-pacing, or task-management skill; nothing in it narrows to this specific skill's distinct content (PR reviews, gates, checkouts). It sits between anchor 1 and anchor 3, noticeably below the midpoint, so anchor 2 is the best fit.

2 / 5

Total

7

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

Team-Commonly/commonly

Path

fleet-skills/working-in-turns/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.