Linkedin Content System

LinkedIn Content System

Use this skill to create credible LinkedIn content from supplied facts, notes, drafts, articles, or source material.

Core rules

1. No invented evidence. Do not invent metrics, client names, event details, quotes, claims, or results.
2. No fake authority. Do not imply the author has done, seen, led, or researched something unless supplied evidence supports it.
3. Keep the voice human. Avoid generic inspirational language, over-polished corporate phrasing, and forced hooks.
4. Fit the format. Match the output to the requested LinkedIn surface: short post, promotional post, event post, newsletter intro, article intro, carousel copy, or long-form article.
5. Avoid unnecessary links or citations in the post body unless the user asks for them. Keep LinkedIn copy clean and paste-ready.

Inputs to look for

• Source article, draft, notes, or bullet points.
• Audience and desired action.
• Author voice guidance.
• Desired length.
• Specific announcement, event, launch, model, or point of view.
• Whether links, hashtags, mentions, or calls to action should be included.

Workflow

1. Read the supplied source material.
2. Extract the central point, proof points, and intended reader response.
3. Choose the appropriate LinkedIn format.
4. Draft in a natural style with clear paragraphs.
5. Keep the post grounded in supplied content.
6. Provide variants if requested.

Output formats

Short post

[Post copy]

Promo post

[Post copy]

[Optional CTA]

Newsletter or article intro

# [Title]

[Intro copy]

Multi-variant output

## Recommended version

[Post]

## Alternative angle

[Post]

## Shorter version

[Post]

Style guidance

• Prefer concrete observations over broad claims.
• Use short paragraphs but avoid a stack of one-line fragments unless the user requests that style.
• Avoid manipulative hooks such as "Stop doing X" unless it genuinely fits the user's tone.
• Make the first line specific enough to be worth reading.
• End with a useful reflection, question, or action rather than a generic CTA.

References

This skill includes supporting reference material. Read the relevant reference file when the task needs additional structure, rubric detail, examples, or checklist support.

• references/linkedin-format-guide.md - use this when additional structure, examples, or checks are useful for the task.

Quality checklist

Before responding, check:

• The content is grounded in supplied facts.
• It reads like a credible human post.
• It fits the requested LinkedIn surface.
• It avoids unnecessary links, references, and invented proof.
• The user can paste it directly into LinkedIn.

Run this — do not improvise

This capability's deterministic implementation is a RAPP single-file agent, linked beside this file as linkedin_content_system_agent.py and embedded as the fenced Python below (sha256 ae1ea403f54f2ecd…; a byte-exact copy is also vaulted in the capsule comment at the end of this file). On a host with sandbox execution, run the linked file directly — if it is missing, write the fence contents verbatim to linkedin_content_system_agent.py first:

python3 linkedin_content_system_agent.py '{"key": "value"}'      # arguments as one JSON object
echo '{"key": "value"}' | python3 linkedin_content_system_agent.py   # or on stdin
python3 linkedin_content_system_agent.py --tool                      # emit the JSON tool contract

Treat stdout as a tool result. If it reports missing or unresolved inputs, stop and collect them. If it returns steps, execute those steps in order exactly as returned; if it returns instructions, follow them with the supplied inputs. Otherwise use the result verbatim. Do not invent behavior beyond that output. On a host without code execution, treat the Parameters schema and the code below as the exact specification and never paraphrase a step. Never edit inside the generated markers; a converter-equipped host can instead restore the original file checksum-verified with the installed rapp-agent-converter/scripts/toast.py convert SKILL.md --to agent.

"""LinkedinContentSystem -- Use this skill when the user asks to create LinkedIn posts, promotional posts, thought-leadership posts, newsletter introductions, article intros, or long-form LinkedIn content from source notes, facts, or drafts.

Generated by the rapp skill from linkedin-content-system. The RCI capsule at the bottom of this file carries the full original; `toast.py convert` restores it byte-exact."""

import json
import re
import sys

try:
    from agents.basic_agent import BasicAgent
except ImportError:  # running OUTSIDE a brainstem -- stay executable anyway.
    class BasicAgent:  # noqa: D101 - minimal stand-in, same contract
        def __init__(self, name=None, metadata=None):
            if name:
                self.name = name
            if metadata:
                self.metadata = metadata

        def perform(self, **kwargs):
            return "Not implemented."

        def system_context(self):
            return None

        def to_tool(self):
            return {"type": "function", "function": {
                "name": self.name,
                "description": self.metadata.get("description", ""),
                "parameters": self.metadata.get("parameters", {})}}

# The procedural layer, verbatim from the source capability.
INSTRUCTIONS = '# LinkedIn Content System\n\nUse this skill to create credible LinkedIn content from supplied facts, notes, drafts, articles, or source material.\n\n## Core rules\n\n1. **No invented evidence.** Do not invent metrics, client names, event details, quotes, claims, or results.\n2. **No fake authority.** Do not imply the author has done, seen, led, or researched something unless supplied evidence supports it.\n3. **Keep the voice human.** Avoid generic inspirational language, over-polished corporate phrasing, and forced hooks.\n4. **Fit the format.** Match the output to the requested LinkedIn surface: short post, promotional post, event post, newsletter intro, article intro, carousel copy, or long-form article.\n5. **Avoid unnecessary links or citations in the post body unless the user asks for them.** Keep LinkedIn copy clean and paste-ready.\n\n## Inputs to look for\n\n- Source article, draft, notes, or bullet points.\n- Audience and desired action.\n- Author voice guidance.\n- Desired length.\n- Specific announcement, event, launch, model, or point of view.\n- Whether links, hashtags, mentions, or calls to action should be included.\n\n## Workflow\n\n1. Read the supplied source material.\n2. Extract the central point, proof points, and intended reader response.\n3. Choose the appropriate LinkedIn format.\n4. Draft in a natural style with clear paragraphs.\n5. Keep the post grounded in supplied content.\n6. Provide variants if requested.\n\n## Output formats\n\n### Short post\n\n```markdown\n[Post copy]\n```\n\n### Promo post\n\n```markdown\n[Post copy]\n\n[Optional CTA]\n```\n\n### Newsletter or article intro\n\n```markdown\n# [Title]\n\n[Intro copy]\n```\n\n### Multi-variant output\n\n```markdown\n## Recommended version\n\n[Post]\n\n## Alternative angle\n\n[Post]\n\n## Shorter version\n\n[Post]\n```\n\n## Style guidance\n\n- Prefer concrete observations over broad claims.\n- Use short paragraphs but avoid a stack of one-line fragments unless the user requests that style.\n- Avoid manipulative hooks such as "Stop doing X" unless it genuinely fits the user's tone.\n- Make the first line specific enough to be worth reading.\n- End with a useful reflection, question, or action rather than a generic CTA.\n\n\n## References\n\nThis skill includes supporting reference material. Read the relevant reference file when the task needs additional structure, rubric detail, examples, or checklist support.\n\n- `references/linkedin-format-guide.md` - use this when additional structure, examples, or checks are useful for the task.\n\n## Quality checklist\n\nBefore responding, check:\n\n- The content is grounded in supplied facts.\n- It reads like a credible human post.\n- It fits the requested LinkedIn surface.\n- It avoids unnecessary links, references, and invented proof.\n- The user can paste it directly into LinkedIn.'

# Ordered commands lifted verbatim from the capability's own documentation.
STEPS = []


class LinkedinContentSystemAgent(BasicAgent):
    def __init__(self):
        self.name = 'LinkedinContentSystem'
        self.metadata = {
          "name": "LinkedinContentSystem",
          "description": "Use this skill when the user asks to create LinkedIn posts, promotional posts, thought-leadership posts, newsletter introductions, article intros, or long-form LinkedIn content from source notes, facts, or drafts.",
          "parameters": {
            "type": "object",
            "properties": {},
            "required": []
          }
        }
        super().__init__(name=self.name, metadata=self.metadata)

    def perform(self, **kwargs):  # toaster:generated-perform
        return json.dumps({"status": "ok", "instructions": INSTRUCTIONS,
                           "inputs": kwargs,
                           "note": "Prose-only capability: follow INSTRUCTIONS "
                                   "with the given inputs."}, indent=2)

if __name__ == "__main__":
    #     echo '{"arg": "value"}' | python3 linkedin_content_system_agent.py
    #     python3 linkedin_content_system_agent.py '{"arg": "value"}'
    #     python3 linkedin_content_system_agent.py --tool          # emit the JSON tool contract
    _a = sys.argv[1:]
    if _a and _a[0] == "--tool":
        print(json.dumps(LinkedinContentSystemAgent().to_tool(), indent=2))
    else:
        _raw = _a[0] if _a else (sys.stdin.read().strip() or "{}")
        print(LinkedinContentSystemAgent().perform(**json.loads(_raw)))

# rci-capsule:v1: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