CtrlK
BlogDocsLog inGet started
Tessl Logo

handoff

Distills the current session's task, context, and plan into a clean, copy-pasteable markdown handoff document for another agent or LLM to pick up. Captures the goal, current state, remaining plan, and the key files, decisions, and gotchas — and leaves out conversational noise, tool-call transcripts, and dead ends. Writes to `.agent/{branch}/handoff.md` and copies it to the clipboard. Use when continuing work in a fresh session, passing a task to a teammate's agent, or briefing a different model. Invoke with /handoff; add a focus phrase to scope the handoff, or --brief for a condensed version.

68

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

77%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.

A well-structured, actionable instruction skill with a clear sequenced workflow, thoughtful fallbacks, and a validating checklist. Its main defects are a broken reference to a missing template file (which also weakens the otherwise fully executable guidance) and some repetition across the Include/Exclude table, Anti-patterns, and Definition of done.

Suggestions

Ship the referenced templates/handoff.template.md (or inline the template's section headings into the body) — step 5 instructs writing the file 'from templates/handoff.template.md', but no such file exists in the bundle.

Deduplicate the rules that appear in both the Include/Exclude table and Anti-patterns (secrets, no placeholders/TODOs, no raw transcripts) and trim the opening paragraph, which restates the frontmatter description.

Add short filled-in examples for the Goal and Current state sections to mirror the good/bad Plan example, so every section the reader must write has a concrete model.

DimensionReasoningScore

Conciseness

The body is dense and mostly earns its tokens — tables, one-line anti-patterns, and a tight good/bad example pair — but the opening paragraph restates the frontmatter description, and the secrets, no-placeholder, and one-line-pointer rules each appear two to three times across the Include/Exclude table, Anti-patterns, and Definition of done. This matches 'efficient with minor instances that could be trimmed' rather than the noticeably-padded anchor 3.

4 / 5

Actionability

Guidance is mostly executable: exact commands ("git rev-parse --abbrev-ref HEAD", "pbcopy < <path>"), a concrete path-resolution chain with fallbacks, and a good/bad example pair citing "src/cli.ts:parseArgs" and line 42. It falls short of anchor 5 because only the Plan section gets a worked example (Goal and Current state do not) and step 5 depends on templates/handoff.template.md, which is not present in the bundle.

4 / 5

Workflow Clarity

Seven clearly sequenced steps with explicit error-recovery fallbacks at each fragile point (non-git cwd falls back to `.agent/handoff.md`, unwritable directory to the scratchpad, missing `pbcopy` is skipped and reported) and a Definition-of-done checklist that validates the output (no secrets, no placeholders, scope stated). This is not a destructive or batch operation, so no cap applies, and it matches the anchor-5 pattern of checkpoints plus feedback for error conditions.

5 / 5

Progressive Disclosure

Sections are well organized with clear headers, and the sole reference ("[templates/handoff.template.md](./templates/handoff.template.md)") is one level deep and clearly signaled — but that file does not exist in the bundle (no templates/, references/, scripts/, or assets/ directories are present). Scored against the actual bundle structure, the single external reference is broken and the section content it should carry is missing, which fits anchor 3 rather than the 'minor organization gaps' of anchor 4.

3 / 5

Total

16

/

20

Passed

Description

92%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 strong description: third-person voice, concrete actions, an explicit output path, and a clear "Use when…" clause with three distinct trigger scenarios. The only gap is modest synonym coverage in trigger terms. No suggestions needed.

DimensionReasoningScore

Specificity

Multiple concrete actions with comprehensive coverage: "Distills the current session's task, context, and plan into a clean, copy-pasteable markdown handoff document", "Captures the goal, current state, remaining plan, and the key files, decisions, and gotchas", and "Writes to `.agent/{branch}/handoff.md` and copies it to the clipboard". It also enumerates exclusions and invocation modes, so it exceeds the 'several specific actions with minor gaps' anchor at 4.

5 / 5

Completeness

Both questions are explicitly answered: the "what" covers distillation, capture, output path, and clipboard copy, and the "when" is an explicit "Use when…" clause with three concrete scenarios. This matches the anchor-5 pattern of concrete trigger phrases, not the softer 'when could be more specific' of anchor 4.

5 / 5

Trigger Term Quality

"Use when continuing work in a fresh session, passing a task to a teammate's agent, or briefing a different model" gives natural trigger phrases, but common variations like "hand off", "summarize the session", or "context transfer" are absent. Good keyword coverage with a few natural terms missing matches anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The niche (session handoff/context transfer to another agent or LLM) is clear with distinct triggers like "continuing work in a fresh session" and "briefing a different model". No closely related skill's triggers overlap these phrases, so it fits the 'clear niche with minimal conflict risk' anchor rather than the minor-overlap anchor at 4.

5 / 5

Total

19

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 1 missing

Warning

Total

13

/

16

Passed

Repository
mthines/agent-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.