CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

continue-implementation

Continue implementing a spec from a previous session

Quality

74%

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 ./.opencode/skills/continue-implementation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 body is a strong, actionable workflow: it sequences steps clearly, provides executable commands, and includes explicit validation checkpoints with feedback loops and well-defined stopping conditions. Its weaknesses are minor — some redundant sections that could be trimmed and slightly incomplete guidance on locating the spec file.

DimensionReasoningScore

Conciseness

The body is efficient — concrete commands, no explanations of concepts Claude already knows — but has minor redundancy: "Read ARCHITECTURE.md" appears in both the task list and the Architecture Awareness section, the Commands section repeats commands already shown inline, and the Begin section restates the task list. Fits anchor 4 (efficient with minor trims possible), not 5.

4 / 5

Actionability

Guidance is mostly executable: specific commands ("git status", "bun run test:run", "bun run lint:fix"), file paths (".agents/plans/", "fixtures/", "#src/*"), and a concrete fixture helper ("loadFixture()"). Minor gaps remain — e.g. no example of how to locate or list spec files in .agents/plans/ — so anchor 4 rather than 5.

4 / 5

Workflow Clarity

The workflow has a clear 8-step sequence, an explicit implement→test→fix→typecheck→lint→repeat loop, explicit validation checkpoints in the stopping conditions ("All tests pass", "Typecheck passes", "Lint passes"), and an error-recovery loop ("If tests fail, fix and re-run"). This matches anchor 5: clear sequence, explicit validation, and feedback loops.

5 / 5

Progressive Disclosure

No bundle files exist, and the body is well-organized into clear sections with one-level-deep, well-signaled references to external project files (ARCHITECTURE.md, CODE_STYLE.md, .agents/plans/). Minor gaps: architecture guidance is restated inline instead of deferring fully to ARCHITECTURE.md, and the Commands section duplicates inline commands — anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

53%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, uses an appropriate imperative voice, and identifies a distinctive niche, but it is minimal: it states a single action with no detail on the skill's actual workflow and provides no "when to use" trigger guidance. It is functional but leaves trigger matching under-specified.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to continue, resume, or finish implementing a spec/plan from a previous session."

List 1-2 more concrete capabilities to raise specificity, e.g. "reads the spec in .agents/plans/, assesses current implementation state, and continues coding until tests, typecheck, and lint pass."

Include natural synonyms users would say ("resume", "pick up where you left off", "finish the plan") to improve trigger term coverage.

DimensionReasoningScore

Specificity

"Continue implementing a spec" names the domain (spec continuation) and one concrete action, but gives no coverage of what the skill actually involves (assessing state, running tests, following architecture). It matches anchor 3 — one clear action, not comprehensive — rather than 4, which requires several specific actions.

3 / 5

Completeness

The description answers "what" ("Continue implementing a spec from a previous session") but has no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because "when" is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

"continue implementing", "spec", and "previous session" are relevant keywords, but common natural variations like "resume", "pick up where you left off", or "finish the plan" are missing. This fits anchor 3 (some relevant keywords, missing variations) rather than 4 (good coverage).

3 / 5

Distinctiveness Conflict Risk

"from a previous session" carves a clear continuation niche distinguishable from general implementation or planning skills, with only minor overlap risk against closely related plan/implementation skills. Not 5 because without explicit triggers, accidental activation on generic "implement this" requests remains possible.

4 / 5

Total

13

/

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

LibPDF-js/core

Path

.opencode/skills/continue-implementation/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.