CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

session-handoff

Write a handoff document so a fresh session or another agent can pick up exactly where this one left off: goal, current state, decisions, next steps and the skills to load, referencing existing files instead of copying them, with secrets redacted before saving. Use whenever the user is ending a session, switching machines, running low on context, or asks for a handoff, a handoff doc, a 'pick up where we left off' summary, or to compact the conversation for next time. Saves to a location the user picks on first run (OS temp, home folder or per-project .handoff/) and can auto-load the latest handoff at the next session start.

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

86%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-engineered, highly actionable skill body: exact templates, executable commands, validation gates, and a genuine one-level reference bundle with no dead links. Weaknesses are minor — some redundancy between Usage/Slash Commands and Redaction vs. its reference file, and the end-to-end flow must be assembled from Examples and the Tools table rather than a single ordered checklist.

Suggestions

Collapse the 'Slash Commands' and 'Usage' sections into one table — they repeat the same /cs-handoff and /cs-handoff-setup entries and env-var toggles.

Add a short ordered 'Workflow' list (trigger → setup → generate → fill via checklist → self_check → linter → save) naming the fix-and-retry step when the strict-mode linter exits 1.

Trim the inline Redaction bullet list to the three or four highest-risk categories and leave the full pattern list to references/redaction_checklist.md.

DimensionReasoningScore

Conciseness

Efficient, instruction-first body with no filler explaining concepts Claude already knows ('Do not paste the diff. Reference the branch or PR.', 'Do not list 20 skills. Pick the 3-5...'). Not 5: minor duplication remains — the Usage table repeats the Slash Commands section, and the Redaction bullet list partially restates what is deferred to references/redaction_checklist.md; not 3: these are trimmable instances, not pervasive padding.

4 / 5

Actionability

Fully executable guidance throughout: exact five-section headers, 'mktemp -t handoff-XXXXXX.md' fallback, 'python3 scripts/handoff_template_generator.py --refresh --goal "<updated goal>"', env toggles 'HANDOFF_SESSIONSTART=0', a Tools table with run order ('Run before the linter'), and worked example dialogs. Copy-paste ready for an instruction-only skill.

5 / 5

Workflow Clarity

The sequence is reconstructable and validation checkpoints exist — handoff_self_check.py 'Run before the linter', redaction_linter.py 'Exit 1 on findings in strict mode' blocking save, plus the mandatory checklist in references/handoff_prompt.md, and Example 1 orders the steps (checklist → scaffold → fill → lint → save). Not 5: no single ordered workflow section, and the fix-and-retry loop after a strict-mode linter failure is implied rather than explicit; not 3: validation is explicitly specified, not absent.

4 / 5

Progressive Disclosure

Clear overview with well-signaled, one-level-deep references that all resolve to real bundle files: references/configuration.md, handoff_structure.md, handoff_prompt.md, deduplication_discipline.md, redaction_checklist.md, assets/example_handoff.md, and seven scripts referenced via the Tools table and refresh command. The body keeps summaries inline and defers full lists ('See ... for the full pattern list') to the right files.

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: it states concrete capabilities, an explicit and richly worded 'Use when' trigger clause with natural user phrases, and a distinct session-continuity niche, all in imperative voice. Minor quibble only: it runs long and packs setup/auto-load details that could be trimmed without loss.

DimensionReasoningScore

Specificity

Multiple concrete actions with comprehensive coverage: 'Write a handoff document', 'referencing existing files instead of copying them', 'secrets redacted before saving', 'Saves to a location the user picks on first run (OS temp, home folder or per-project .handoff/)', and 'auto-load the latest handoff at the next session start'. Not 4: coverage spans write, dedup, redact, save-location options, and auto-load with no notable gaps.

5 / 5

Completeness

Explicitly answers both: what ('Write a handoff document so a fresh session or another agent can pick up exactly where this one left off: goal, current state, decisions, next steps and the skills to load') and when ('Use whenever the user is ending a session, switching machines, running low on context, or asks for a handoff...') with concrete trigger phrases. Not 4: the when-clause is explicit and specific, not merely present.

5 / 5

Trigger Term Quality

Comprehensive natural terms and synonyms: 'ending a session, switching machines, running low on context', 'a handoff, a handoff doc, a pick up where we left off summary, or to compact the conversation'. These are phrases users would actually say; not 4 because no common variation is noticeably missing.

5 / 5

Distinctiveness Conflict Risk

Clear niche (session handoff/continuity) with distinct triggers ('handoff doc', 'pick up where we left off', 'compact the conversation for next time') that are unlikely to fire for unrelated skills. Not 4: the overlap with generic conversation-summarization is minimal because every trigger is anchored to the handoff/session-continuation intent.

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

alirezarezvani/claude-skills

Path

productivity/handoff/skills/session-handoff/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.