DC postfast
Schedule and manage social media posts across TikTok, Instagram, Facebook, X (Twitter), YouTube, LinkedIn, Threads, Bluesky, Pinterest, Telegram, and Google Business Profile using the PostFast API. Use when the user wants to schedule social media posts, manage social media content, upload media for social posting, list connected social accounts, check scheduled posts (filtered by account, platform, status or date), delete posts one at a time or up to 100 per call, cross-post content to multiple platforms, manage Google Business Profile posts, geotag posts with real-world places, pick trending pre-cleared TikTok sounds for photo and carousel posts, read or reply to the comments on their posts (social inbox on TikTok, Instagram, Facebook, Threads), triage or moderate comment conversations, generate a connect link so an agency client or their own app's user can connect accounts without a PostFast account, or automate their social media workflow. PostFast is a SaaS tool, no self-hosting required.
Schedule and manage social media posts across TikTok, Instagram, Facebook, X (Twitter), YouTube, LinkedIn, Threads, Bluesky, Pinterest, Telegram, and Google…
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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 · 5
✓ No critical or high findings
Medium and low: 5
-
medium Exfiltration
net-credential-useSKILL.md:32Credential used in a network call (verify the destination is the intended service)curl -s -H "pf-api-key: $POSTFAST_API_KEY" https://api.postfa.st/social-media/my-social-accounts
-
medium Exfiltration
net-credential-useSKILL.md:108Credential used in a network call (verify the destination is the intended service)curl -s -H "pf-api-key: $POSTFAST_API_KEY" "https://api.postfa.st/social-posts?page=0&limit=20"
-
medium Exfiltration
net-credential-useSKILL.md:141Credential used in a network call (verify the destination is the intended service)curl -X DELETE -H "pf-api-key: $POSTFAST_API_KEY" https://api.postfa.st/social-posts/POST_ID
-
medium Exfiltration
net-credential-useSKILL.md:236Credential used in a network call (verify the destination is the intended service)curl -s -H "pf-api-key: $POSTFAST_API_KEY" \
-
medium Exfiltration
net-credential-useSKILL.md:283Credential used in a network call (verify the destination is the intended service)curl -s -H "pf-api-key: $POSTFAST_API_KEY" \
Files scanned: 39. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 1007 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
body-longSKILL.md body ≈ 17355 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage" - note
edit-residuethe text marks something as outdated (lines 343, 575): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 10Execution cost. Instruction body is 17355 tokens: crowds the task out of the window
- 30Running it twice. 85 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Consistency. The Hermes dialect needs category and tags
- 85Steps. 184 steps, 2 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 3 branches, has a failure section
- 100Progress reporting. Reports progress
- 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 (9 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 1007: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 44 headings
- +3Step-by-step instructions: 184 items
- +4Has examples (31 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.