BC tinker-linkedin
Your agent crawls LinkedIn through the browser session you already have — profiles, search, connections, inbox, feed. No official API, no app review. Your cookies never leave the browser: every call is a fetch() run inside the linkedin.com tab you shared, and 1.2.1 DELETED the cookie-extraction, session-store and external-replay code from the package rather than leaving it switched off — there is no longer anything to store or steal. Every request, navigation and tab pick is pinned to exactly https://www.linkedin.com, including the LINKEDIN_TARGET_ID override, so a look-alike host cannot borrow your session. Reads and drafts freely; the one write, message-send, needs per-action consent that repeats the exact conversation URN, and without it you get the draft and nothing is sent. The browser relay must be on loopback, with no override. Built for the TinkerClaw fork — github.com/globalcaos/tinkerclaw. See Permissions, Data Flow & Consent.
Your agent crawls LinkedIn through the browser session you already have — profiles, search, connections, inbox, feed.
As a process C 50/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5627 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "repository" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 50/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 32 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, git, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 5627 tokens
- 85Steps. 48 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (14 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 950: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +4Structure: 22 headings
- +3Step-by-step instructions: 48 items
- +4Has examples (6 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.