agentleFS
getedgehqgetedgehq/skills/braun-poke-the-bear/SKILL.md

braun-poke-the-bear

Skill5 starsChanged 13 days agoApache-2.0View on GitHub

Create and review cold-call talk tracks and cold emails using Josh Braun's Poke the Bear method. Use to examine a prospect's current process, surface a possible overlooked cost, and invite discussion without leading questions or sales pressure.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read references/method.md for the reasoning and channel decisions.

    line 16
  2. Distinctive:

    Listen and reflect before deepening: After a response, pause briefly, then reflect or clarify what was actually said.

    line 34
  3. Distinctive:

    Offer a conditional next step: When interest appears, connect the capability to their described process, then ask whether a later …

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Josh Braun's Poke the Bear

Based on Josh Braun's public method. Not affiliated with or endorsed by Josh Braun.

When to use

Use this skill when drafting a prospecting call, adapting its central question to cold email, repairing a disguised pitch, or reviewing outreach that attracts reflexive dismissals. The deliverable is a prospecting brief plus a usable call or email, with response branches that preserve the prospect's choice. Begin with the job the person performs and how they accomplish it today, rather than the seller's preferred product story. [S1][S2][S3]

The method is especially useful when a familiar supplier or workaround appears adequate but a separate exposure may remain unexamined. It does not establish that the prospect has a problem. A satisfactory current process, the wrong responsibility, and a refusal are valid discoveries. Do not convert the exercise into a meeting quota, a fear campaign, or a sequence of rebuttals. [S4][S8][S12]

Read references/method.md for the reasoning and channel decisions. The sequence below is this package's operational synthesis: Braun's public examples vary, and he explicitly emphasizes intent over a universal script. The examples and template are teaching tools, not scripts he authored. [S7]

Procedure

  1. Define the assignment and success. Identify the channel, intended role, job, and seller capability. Set success as learning whether a relevant gap and willingness to discuss it exist. Drafting outreach does not itself authorize sending it. Use the intake fields in templates/output-template.md and the intent rules in references/method.md. [S3][S8]
  2. Separate facts from hypotheses. Record verified role information, known workflow details, and unknowns. Mark assumed processes and possible consequences explicitly. Do not invent customers, losses, or statistics to make the opening compelling. Consult the evidence rules in references/method.md and trace any method attribution through references/sources.md. [S4][S7]
  3. Map one overlooked exposure. Describe the current approach, the concrete mechanism that could leave something unseen, and its possible consequence. Prefer a specific verification gap over generic savings language. If no defensible exposure exists, ask about the process before proposing one. See the problem map in references/method.md. [S2][S4]
  4. Choose a brief, relevant opening. For calls, identify yourself and select a direct or permission opening. Verify responsibility when unknown; use a tentative observation when research supports it. Include peer familiarity only when true. Avoid stacking introductions and qualification questions. See the opening decisions in references/method.md. [S1][S5][S7][S11]
  5. Frame the possibility without accusation. If context is needed, describe a recognizable situation and leave room for it not to apply. Use a peer observation only when supported. Keep product explanation for the point where it helps answer the prospect's question. Follow the framing rules in references/method.md. [S3][S6]
  6. Write one neutral process question. Ask how or what they currently do about the job or exposure. Check whether a satisfied prospect can answer comfortably. Add a small, correctable menu only when it reduces effort. Compare the weak and improved drafts in examples/worked-examples.md. [S2][S5][S12]
  7. Create space for the answer. Put a pause after the call question. For email, make the question the reply point and remove competing requests. Keep spoken stretches short and conversational. Use the channel fields in templates/output-template.md and delivery guidance in references/method.md. [S1][S2][S12]
  8. Listen and reflect before deepening. After a response, pause briefly, then reflect or clarify what was actually said. Alternate questions with grounded observations. Explore a revealed gap rather than inventing the next admission. See the listening rules in references/method.md. [S9][S11]
  9. Write distinct response branches. Cover an adequate process, a gap, a refusal, interest, and uncertain ownership. Accept satisfaction and stop on an explicit refusal. Clarify a dismissal only if the person remains willing to converse. Use the branch fields in templates/output-template.md. [S8][S12]
  10. Offer a conditional next step. When interest appears, connect the capability to their described process, then ask whether a later conversation would help. Honor the promised brevity. Consult the progression rules in references/method.md and the call illustration in examples/worked-examples.md. [S1][S5][S10]
  11. Review and deliver. Apply checklists/review-checklist.md, repair every failed item, and return the brief, finished message, branches, and a short neutrality rationale. State unresolved evidence gaps rather than concealing them. [S3][S8][S12]

Files in this skill

  • references/method.md: Detailed principles, decisions, edge cases, and expert warnings.
  • references/sources.md: The twelve fetched public sources and their contributions.
  • examples/worked-examples.md: Invented call and email illustrations with before-and-after analysis.
  • templates/output-template.md: Fill-in prospecting brief, channel draft, branches, and rationale.
  • checklists/review-checklist.md: Pass/fail review criteria and common repairs.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.