CtrlK
BlogDocsLog inGet started
Tessl Logo

sessions

Core principles and workflow router for changes to the Agents Window under src/vs/sessions.

60

Quality

70%

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 ./.github/skills/sessions/SKILL.md
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 workflow router with concrete paths, commands, and interface contracts, and excellent progressive disclosure through its specification routing table. Its main gaps are minor: an absent failure-recovery loop after validation and slight overlap between the feedback-related sections.

Suggestions

Add one line to the validation section covering failure handling, e.g. 'If a check fails, fix and re-run it before proceeding' to close the feedback loop.

Merge the overlapping guidance in sections 6 and 7 (both cover where feedback/learnings belong) into a single section.

Name the specific specialist skills to invoke (accessibility, design, etc.) if they have stable names, replacing the vague 'applicable specialist skill'.

DimensionReasoningScore

Conciseness

The body is dense, directive, and assumes competence — every bullet states a rule, path, or command with no concept explanations. It falls just short of anchor 5 because sections 6 and 7 overlap on feedback handling and some phrasing ('represent shared capability, not Sessions-specific policy') could be tightened. It is well above anchor 3 since there is no padding or over-explanation.

4 / 5

Actionability

Guidance is concrete and executable: exact file paths ('browser/menus.ts', 'sessions.*.main.ts'), a runnable command ('npm run valid-layers-check'), named contracts ('ISessionsManagementService', 'ISession', 'IChat'), and a routing table of specifications. It is not a 5 because a few directives remain vague ('invoke the applicable accessibility... skill') and no example of applying the principles is given; it clearly exceeds anchor 3 since no pseudocode or hand-waving fills the gaps.

4 / 5

Workflow Clarity

The seven numbered sections give a clear sequence — principles, identify owning area, inspect, implement, validate proportionally, record feedback, maintain — with an explicit validation step naming the smallest checks to run. It misses anchor 5 because there is no error-recovery loop (what to do when 'valid-layers-check' or tests fail), and it is above anchor 3 because validation checkpoints are explicit and concrete rather than implicit.

4 / 5

Progressive Disclosure

The body is itself a router: a start point ('src/vs/sessions/README.md'), a table mapping each concern to exactly one one-level-deep specification file, a search-before-read rule for the learning inbox, and per-section pointers to specialist skills. No bundle files exist alongside the skill, so structure is judged on the body itself, which matches 'Clear overview with well-signaled one-level-deep references; easy navigation'.

5 / 5

Total

17

/

20

Passed

Description

61%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 has a distinct, path-scoped trigger that makes it highly distinguishable, but the capability statement is abstract. Naming two or three concrete actions (e.g. implementing, reviewing, or designing sessions changes) alongside the existing trigger would raise specificity and completeness.

Suggestions

Replace 'Core principles and workflow router' with concrete action verbs, e.g. 'Implements, reviews, and routes design work for changes to the Agents Window under src/vs/sessions'.

Add one or two natural synonyms users might say, such as 'sessions' or 'session/chat work', to broaden trigger coverage.

Make the what/when pairing explicit with a 'Use when making changes to...' clause so both halves are unmistakable.

DimensionReasoningScore

Specificity

The description names the domain ('changes to the Agents Window under src/vs/sessions') but the capabilities are abstract — 'Core principles and workflow router' names roles rather than concrete actions like extracting, analyzing, or reviewing. It matches the anchor 'Names the domain but actions are minimal or generic'; it is not a 3 because no concrete, verb-driven action is stated.

2 / 5

Completeness

It explicitly answers 'when' ('for changes to the Agents Window under src/vs/sessions') and states a 'what' ('Core principles and workflow router'), so it avoids the missing-trigger cap of 3. It is not a 5 because the 'what' is abstract rather than concrete capabilities, and not a 3 because the when-clause is explicit, not weakly implied.

4 / 5

Trigger Term Quality

'Agents Window', 'src/vs/sessions', and 'changes' are natural terms a developer would say, but common variations and synonyms are missing (e.g. 'sessions', 'session list', 'Sessions sidebar'). It matches 'Some relevant keywords but missing common variations or synonyms'; not a 4 because keyword coverage is thin and not a 2 because the keywords are domain-natural rather than generic.

3 / 5

Distinctiveness Conflict Risk

The path-scoped trigger ('src/vs/sessions', 'Agents Window') carves out a clear niche with minimal overlap risk against other skills — a user naming this area would reliably hit this skill. It matches the anchor 'Clear niche with distinct triggers; minimal conflict risk'.

5 / 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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
posit-dev/positron
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.