SKILLEMALL.ai
GitHub ↗ RU Sign in

AA clipboard-memory

Recall what the user copied on this Mac via the local clipmem archive — text, commands, URLs, file paths, HTML, images, PDFs. Triggers on requests like "what was that command I copied?", "the URL I copied from Safari", "find that snippet before I restarted", or any paraphrase involving copy, paste, or clipboard. Offers ranked recall, chronological timeline, lexical / FTS search, raw-byte export for binary content, cursor pagination, and filters by app, kind, time window, and content shape. Use before reaching for generic web or repo search whenever the user is trying to recover something they previously had on the clipboard.

ClawHub Agent Skills author: Tristan Manchester v1.3.9 MIT-0 8 files · 1 script body ≈ 2 289 tokens Open the sourceclawhub.ai↗ analyzed 13 h ago

Recall what the user copied on this Mac via the local clipmem archive — text, commands, URLs, file paths, HTML, images, PDFs.

As a process A 82/100 · Runs to the end — weak spots: running it twice, progress reporting

ProcedureSoftware developmentWriting and documentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
99/100
safety, quality, tests
Safety 60%
98
Quality 40%
100
Run on models
none yet
Process rating
A
82/100
Runs to the end
Progress reporting w 2
0
Running it twice w 4
30
Tools and files w 18
60
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 2

    ✓ No critical or high findings

    Medium and low: 2
    • low Dangerous commands cmd-persistence references/examples.md:120
      Persistence mechanism (cron / launchd / scheduled task / autorun registry) (test fixture / example file; quoted — discussed, not commanded)
      clipmem search "launchctl bootstrap" --mode literal --format json --limit 25
      fixturequoted
    • low Dangerous commands cmd-persistence references/examples.md:134
      Persistence mechanism (cron / launchd / scheduled task / autorun registry) (test fixture / example file; quoted — discussed, not commanded)
      clipmem search "launchctl bootstrap" --mode literal --format json --limit 25 \
      fixturequoted

    Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 82/100

    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 1 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 100Steps. 46 steps
    • 100When it triggers. States when to use and when not to
    • 100Inputs and preconditions. Inputs and preconditions are listed
    • 100Failures and branches. 1 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2289 tokens
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 13 top-level sections: this looks like several domains in one skill
    • low The response is described with custom markup (6 tags): a typed call is more reliable

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +4Description does not say when NOT to use the skill (false activations)
    • +2Single-language instructions
    • +5Description quotes 3 example trigger phrases
    • +3Description length 632: enough signal without eating the budget
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 46 items
    • +3Output format is stated explicitly
    • +4Has examples (1 code blocks)
    • +4Reference files are cited in the instructions (5 of 5)
    • +3All 1 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 100.

    External checks

    ClawHub: suspicious
    This skill is coherent for local clipboard recall, but it needs Review because it can reveal exact historic clipboard contents and installs a mutable external clipboard watcher with persistent and state-changing capabilities.
    LLM: suspicious (high) · 13 Sept 2026