All skills
deanpeters avatar

/competitive-intel-watch

@eb7a51e

Scheduled delta monitoring against a prior competitive snapshot. Use when tracking competitors on a cadence: material shifts only, cited evidence, battle-card update flags, runs unattended.

Use this Skill: https://skilld.dev/gh/deanpeters/product-manager-skills/competitive-intel-watch

This session only. Nothing lands on disk.

examplessample.md

≈1.2k tokens on demand. Your agent reads this file only when SKILL.md points to it.

Competitive Intel Watch — Worked Example

All companies, products, URLs, and figures are fictional. This example continues the chain: the competitive-research-snapshot example (Fieldlight vs. Wrenchline, DispatchCrow, Vantiga FSM, dated 2026-06-28) is the baseline this run diffs against. The update flags below are what the battle-card-builder example consumes.

Invocation: Competitive intel watch — prior snapshot pasted below (dated Jun 28); this cycle I'm specifically watching for DispatchCrow shipping capacity planning. [snapshot]

Both budget questions were answered inline (snapshot provided, watch focus stated), so the skill asked nothing, read the snapshot fully, showed its search plan, and swept.


Competitive Watch Report

1. Run Header

Scope (from prior snapshot): Fieldlight vs. FSM competitors; decision context: FSM expansion leading with quoting Prior snapshot date: 2026-06-28 This run date: 2026-07-28 Competitors checked: Wrenchline, DispatchCrow, Vantiga FSM

2. Changelog (Material Shifts Only)

Wrenchline — launched "Wrenchline Essentials" entry tier

  • What changed: new $79/month tier for shops under 25 techs appeared on the pricing page; no dispatch board, no payroll — scheduling, quoting, invoicing only — Fact (pricing page vs. archived version, Jul 24 vs. Jun 28)
  • Evidence: URL + archive diff, dated Jul 24, 2026
  • So what: this is the "lite tier to defend the low end" we filed as an Assumption in the June snapshot — now confirmed. It lands directly on Fieldlight's segment and includes the quoting we haven't shipped yet. Pricing owner and roadmap owner both act on this.
  • Confidence: high

DispatchCrow — two senior hires from Wrenchline's dispatch team

  • What changed: DispatchCrow announced a "head of dispatch experience" and a senior PM, both ex-Wrenchline per their own announcement post — Fact (company blog, Jul 15); capacity planning is coming — Inference (that's the expertise those hires carry; no roadmap statement yet)
  • Evidence: URL, dated Jul 15, 2026
  • So what: the competitive risk from the June snapshot ("DispatchCrow closes their dispatch gap while we open ours") just moved from Assumption toward likely. Roadmap owner acts: the window for quoting-first expansion is real but narrower than planned.
  • Confidence: medium (hires are Fact; the product conclusion is Inference)

Vantiga FSM: nothing cleared the bar. Two blog posts and a webinar — routine content marketing.

3. Update Flags

Downstream artifact Sections needing update Driven by
Battle card Pricing & Packaging Snapshot; Do Not Say ("we're the affordable option" now contested) Wrenchline Essentials tier
Pricing/packaging analysis Entry-tier comparison table Wrenchline Essentials tier
Roadmap assumptions Quoting-first timeline; dispatch-gap window DispatchCrow hires

4. Watchlist for Next Run

  • DispatchCrow changelog for any dispatch-board or capacity-planning beta (the hires suggest 1-2 quarters out)
  • Wrenchline Essentials review volume — whether the tier is real motion or a defensive press release
  • Vantiga Go independent reviews (still only two; evidence quality on that column remains low)

Assumptions to Validate

  • Wrenchline Essentials excludes the dispatch board permanently, not just at launch
  • DispatchCrow's new hires are building capacity planning rather than polishing the existing board
  • Our "quote from the calendar" differentiator still has no direct equivalent shipping elsewhere

Why this example works

  • It reports change, not state. Three competitors were swept; the report contains two entries and one explicit "nothing cleared the bar." A regenerated full snapshot would have buried both signals in ten sections of unchanged prose.
  • The diff paid off against the baseline's own assumptions. The June snapshot filed "Wrenchline bundles a lite tier" as an Assumption with no signal; this run confirmed it with an archive diff. That's the compounding value of a stable schema — assumptions become tripwires.
  • Labels stayed honest under excitement. The DispatchCrow hires are a Fact; "capacity planning is coming" stays an Inference with its basis shown, and confidence is marked medium, not high.
  • The update flags close the loop. Each material shift names the artifact and section it stales — the battle card flags here are exactly what the battle-card-builder example picks up.

Source: SKILL.md on GitHub

1 warning2mo3 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    This skill is a competitive intelligence workflow designed to monitor market shifts by comparing new web data against previous research snapshots. It identifies changes in competitor pricing, positioning, and roadmaps. The skill includes built-in safety features such as requiring cited evidence for all claims and establishing human-review checkpoints for scheduled or unattended executions. No security issues were detected.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: MEDIUM · 1 issue

Signed by skilld at eb7a51e. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Activeupdated 3 months ago
argument-hint
[prior snapshot (pasted/attached), and anything specific to watch]
type
workflow
theme
market-intelligence
Other metadata
intent
A competitive intelligence delta monitor: given a previous Competitive Research Snapshot, sweep for material shifts since the last run and report only what changed — a cited changelog plus flags naming which battle card or positioning sections now need updating. Designed to run unattended on a loop or schedule; an empty changelog is a valid, useful result.
best_for
[
  "Keeping battle cards and positioning current without regenerating research weekly",
  "Running unattended on a schedule and reporting only changes a rep or roadmap owner would act on",
  "Turning competitive research from a one-off deliverable into a standing capability"
]
scenarios
[
  "Run this against last quarter's snapshot and tell me what actually changed",
  "Set up a monthly competitor watch that flags when our battle card goes stale"
]
estimated_time
10-25 min per run (after the baseline exists)

README badge

README badge for deanpeters/product-manager-skills/competitive-intel-watch