CtrlK
BlogDocsLog inGet started
Tessl Logo

continue-codex-work

Continues interrupted Codex work only after read-codex-history verifies rollout identity and fork/compaction lineage — restores the original outcome, unfulfilled requests, and the next action. Use when given a Codex Session ID, asked to pick up a prior Codex run, told Codex was interrupted, fused, compacted or stuck, or asked to take over without `codex resume`. Not for a conversation Codex already natively resumed.

74

Quality

93%

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

85%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 a tightly written, well-sequenced takeover workflow with strong validation gates, fail-closed error handling, and an appropriately placed single reference. Its only weaknesses are mild: some dense nested prose that could be tightened and guidance that is procedural rather than command-complete.

DimensionReasoningScore

Conciseness

The body is instruction-dense with no filler and no explanations of concepts Claude already knows, but a few passages run long with nested clauses (e.g., the Step 3 in-flight paragraph embedding the shell pattern in a parenthetical) that could be trimmed or split. Efficient overall with minor over-length — the 4 anchor, not the 5 anchor's 'every token earns its place'.

4 / 5

Actionability

Concrete throughout: a named skill invocation ('daymade-claude-code:read-codex-history'), a receipt checklist, a contract table with per-field evidence requirements, one copy-paste shell pattern, and explicit do-nots ('Do not run `codex resume`'). Mostly executable guidance with minor gaps — the workflow is procedural judgment work rather than fully command-complete — fitting the 4 anchor better than 5.

4 / 5

Workflow Clarity

Clear 5-step sequence (receipt → contract → reconcile → execute → report) with explicit fail-closed validation conditions, feedback loops ('expand verification only for new changes, failures or unresolved evidence gaps', 'close its feedback loop'), and a final report checklist keyed to the contract. Matches the 5 anchor's explicit validation steps, error-recovery loops, and checklists.

5 / 5

Progressive Disclosure

A single well-signaled one-level-deep reference ([Native Goal reconciliation](references/native-goal-reconciliation.md)) linked exactly at the point of need; the file exists and references nothing further. The core workflow stays inline and the specialized Native Goal procedure is appropriately split out, matching the 5 anchor.

5 / 5

Total

18

/

20

Passed

Description

100%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 exemplary: concrete third-person actions, an explicit 'Use when' clause with natural trigger phrases and synonyms, and a clear negative boundary that prevents mis-triggering on native resumes. It covers what, when, and when-not with no padding.

DimensionReasoningScore

Specificity

Multiple concrete actions in third-person voice: "Continues interrupted Codex work", "verifies rollout identity and fork/compaction lineage", "restores the original outcome, unfulfilled requests, and the next action". Coverage is comprehensive across verify/restore/next-action, matching the 5 anchor; no minor gaps that would justify 4.

5 / 5

Completeness

Explicitly answers both questions: what ("restores the original outcome, unfulfilled requests, and the next action") and when ("Use when given a Codex Session ID, asked to pick up a prior Codex run, told Codex was interrupted, fused, compacted or stuck..."), plus a negative boundary ("Not for a conversation Codex already natively resumed"). Matches the 5 anchor exactly.

5 / 5

Trigger Term Quality

Natural user phrasings with synonyms: "given a Codex Session ID", "pick up a prior Codex run", "Codex was interrupted, fused, compacted or stuck", "take over without `codex resume`". This matches the 5 anchor's comprehensive synonym coverage; the 4 anchor's "a few natural terms missing" does not apply.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Codex takeover after verified history read) with distinct triggers and an explicit exclusion separating it from native resume, so overlap with other skills is minimal. Matches the 5 anchor.

5 / 5

Total

20

/

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
daymade/claude-code-skills
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.