Proposal Research Dossier Builder

What it does

When your agent uses it

• Researching a client and their tech stack before writing a proposal
• Matching a new opportunity against past case studies in an indexed library
• Gathering pricing benchmarks or competitive context for a pitch or RFP
• Building a polished research dossier to back up a proposal's claims

Example prompts

• “Build a research dossier for this RFP using the brief in the current run folder.”
• “Match this client's needs against our case-study index and summarize the fit.”
• “Research this prospect's tech stack and typical budget range for a project like theirs.”
• “Run the research step headless, using only our local case-study notes.”

Requirements

• Python to run the bundled render_dossier.py script
• A structured brief.md file in the proposal's run folder
• Optionally a case-studies-index.json file and live web research access

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1Find the run folder. If the user gave a path, use it. Else scan {workspace_folder}/*/brief.md — most recent or ask which run. If none…
2. 2Read the brief. Load {run-folder}/brief.md. Extract client name, scope, requirements, industry signals. Derive {client-slug} (lowercase…
3. 3Read shared memory. Load {memory-root}/index.md, {memory-root}/library/case-studies-index.json, and…
4. 4Pick research mode. See Research mode routing below.

What it can do on your machine

Read from SKILL.md and the folder at commit 547a6df. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 4 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python3

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • pawbytes.io

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Proposal Research Dossier Builder loads about 2.2k tokens when it runs, and up to ~6.4k if it reads all its reference files. Until then it costs about 111 tokens; SKILL.md has 886 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~111

When it runs · the whole SKILL.md, loaded when a task matches

~2.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~6.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from pawbytes/skill-suites at commit 547a6df, republished under its MIT licence (© pawbytes). 886 words, ~2,225 tokens.

name

paw-pa-research

description

Proposal research workflow that matches local case studies and gathers web evidence into an HTML research dossier. Use when the user needs proposal research, client intel, tech stack discovery, pricing benchmarks, competitive context, or case-study matching for a brief. Triggers: 'research this proposal', 'build a research dossier', 'match case studies', 'find pricing benchmarks', 'client intel for', 'what tech does X use'.

{
  "id": "cs-001",
  "client": "Prior Client Co",
  "industry": "Manufacturing",
  "serviceType": "Shopify migration",
  "deliverables": ["Theme rebuild", "ERP integration"],
  "outcome": "40% conversion lift in 90 days",
  "testimonial": "Optional quote",
  "tags": ["shopify", "b2b", "ecommerce"],
  "sourceDocPath": "library/inbox/prior-proposal.pdf"
}

python3 scripts/render_dossier.py --findings "{run-folder}/.research-findings-{date}.json" --out "{run-folder}/research-dossier.html"

© pawbytes, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 13 other files (scripts, references) in src/pa/paw-pa-research of pawbytes/skill-suites.

• SKILL.md
• references/client-intel.md
• references/competitive-context.md
• references/cursor-browser-research.md
• references/live-browser-research.md
• references/local-case-study-matching.md
• references/local-only-research.md
• references/pricing-benchmarks.md
• references/tech-stack-research.md
• references/web-evidence.md
• scripts/__pycache__/render_dossier.cpython-311.pyc
• scripts/render_dossier.py
• scripts/tests/__pycache__/test-render_dossier.cpython-311-pytest-9.0.2.pyc
• scripts/tests/test-render_dossier.py

Open the folder on GitHubat commit 547a6df