AC hashtag-strategy
Use to build a hashtag and discoverability strategy for social posts — the modern (2026) approach, not the outdated "30 hashtags to go viral" playbook. Run when the user says "hashtags," "what hashtags should I use," "how many hashtags," "hashtag strategy," "help me get discovered/reach," asks "do hashtags still work / are hashtags dead," or asks how to tag a post. Reads brand-profile and audience first. Sets the keyword/social-SEO layer first (caption, on-screen text, spoken audio) because that — plus engagement and the content itself — drives discovery far more than hashtags now; then picks a tight, relevant, per-platform hashtag set (respecting caps like Instagram's enforced 5-tag limit), favors niche/mid-tier tags over generic mega-tags, and designs branded/campaign hashtags for community and tracking. Rotates sets rather than copy-pasting one block, and hands placement/publishing to scheduling-and-queue. Sets honest expectations: hashtags categorize and aid search; they are not a reach hack.
Use to build a hashtag and discoverability strategy for social posts — the modern (2026) approach, not the outdated "30 hashtags to go viral" playbook.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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: 6. 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 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 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
- 100Tools and files. No external tools needed
- 100Steps. 30 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1205 tokens
- medium 9 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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 1011: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Structure: 10 headings
- +3Step-by-step instructions: 30 items
- +4Reference files are cited in the instructions (4 of 4)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.