FF x-bookmark-triage
Automatically triages X/Twitter bookmarks into structured knowledge cards and posts them to a Discord channel (#knowledge-intake or similar). Captures tweet content via fxtwitter, scores relevance using Claude Haiku, assigns tier (1–10), freshness (evergreen/dated/expired), and topic tags, then optionally unbookmarks after capture. Includes a scheduled poll for new bookmarks, a one-time backlog sweep, and a manual drop handler. Use when: (1) setting up automated bookmark → knowledge card pipeline, (2) draining an existing bookmark backlog, (3) dropping a URL manually for immediate triage, (4) packaging this as a publishable skill for other OpenClaw users. Requires X OAuth 2.0 User Context with bookmark.read scope (+ bookmark.write to unbookmark). Triggers on: "triage my bookmarks", "set up bookmark pipeline", "drain bookmark backlog", "x-bookmark-triage", "knowledge intake".
As a process F 53/100 · Will not run — References files that are not bundled: scripts/ai.watson.knowledge-intake-poll.plist
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- The text references files that are not there: add them or drop the references.
- 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 · 9
-
high Dangerous commands
cmd-persistenceREADME.md:69Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/ai.watson.knowledge-intake-poll.plist
-
high Dangerous commands
cmd-persistencereferences/adapting.md:125Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/ai.watson.knowledge-intake-poll.plist
-
high Dangerous commands
cmd-persistencereferences/cron-setup.md:63Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/ai.watson.knowledge-intake-poll.plist
-
high Dangerous commands
cmd-persistencereferences/cron-setup.md:68Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl unload ~/Library/LaunchAgents/ai.watson.knowledge-intake-poll.plist
-
high Dangerous commands
cmd-persistenceSKILL.md:111Persistence mechanism (cron / launchd / scheduled task / autorun registry)cp scripts/ai.watson.knowledge-intake-poll.plist ~/Library/LaunchAgents/
-
high Dangerous commands
cmd-persistenceSKILL.md:112Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/ai.watson.knowledge-intake-poll.plist
Medium and low: 3
-
medium Dangerous commands
cmd-persistencescripts/run-poll.sh:17Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)PLIST="${OPENCLAW_GATEWAY_PLIST:-$HOME/Library/LaunchAgents/ai.openclaw.gateway.plist}"code literal -
medium Dangerous commands
cmd-persistencescripts/setup-check.js:76Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)console.log(' - Edit: ~/Library/LaunchAgents/ai.openclaw.gateway.plist');code literal -
medium Dangerous commands
cmd-persistencescripts/setup-check.js:78Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)console.log(' - Reload: launchctl unload ... && launchctl load ...');code literal
Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/ai.watson.knowledge-intake-poll.plist
Process rating: all ten parameters 53/100
- 0Tools and files. 1 referenced file(s) missing: scripts/ai.watson.knowledge-intake-poll.plist
- 0Result and completion. Does not say what the result is
- 30Running it twice. 7 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 45 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1979 tokens
- 100Progress reporting. Reports progress
- low 13 top-level sections: this looks like several domains in one skill
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)
- +3Description length 887: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -31 of 7 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Structure: 22 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (12 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.